Daily Papers

Chain-of-thought reasoning, a cognitive process fundamental to human intelligence, has garnered significant attention in the realm of artificial intelligence and natural language processing. However, there still remains a lack of a comprehensive survey for this arena. To this end, we take the first step and present a thorough survey of this research field carefully and widely. We use X-of-Thought to refer to Chain-of-Thought in a broad sense. In detail, we systematically organize the current research according to the taxonomies of methods, including XoT construction, XoT structure variants, and enhanced XoT. Additionally, we describe XoT with frontier applications, covering planning, tool use, and distillation. Furthermore, we address challenges and discuss some future directions, including faithfulness, multi-modal, and theory. We hope this survey serves as a valuable resource for researchers seeking to innovate within the domain of chain-of-thought reasoning.

Multi-turn-to-single-turn (M2S) compresses iterative red-teaming into one structured prompt, but prior work relied on a handful of manually written templates. We present X-Teaming Evolutionary M2S, an automated framework that discovers and optimizes M2S templates through language-model-guided evolution. The system pairs smart sampling from 12 sources with an LLM-as-judge inspired by StrongREJECT and records fully auditable logs. Maintaining selection pressure by setting the success threshold to theta = 0.70, we obtain five evolutionary generations, two new template families, and 44.8% overall success (103/230) on GPT-4.1. A balanced cross-model panel of 2,500 trials (judge fixed) shows that structural gains transfer but vary by target; two models score zero at the same threshold. We also find a positive coupling between prompt length and score, motivating length-aware judging. Our results demonstrate that structure-level search is a reproducible route to stronger single-turn probes and underscore the importance of threshold calibration and cross-model evaluation. Code, configurations, and artifacts are available at https://github.com/hyunjun1121/M2S-x-teaming.

Multiple business scenarios require an automated generation of descriptive human-readable text from structured input data. Hence, fact-to-text generation systems have been developed for various downstream tasks like generating soccer reports, weather and financial reports, medical reports, person biographies, etc. Unfortunately, previous work on fact-to-text (F2T) generation has focused primarily on English mainly due to the high availability of relevant datasets. Only recently, the problem of cross-lingual fact-to-text (XF2T) was proposed for generation across multiple languages alongwith a dataset, XALIGN for eight languages. However, there has been no rigorous work on the actual XF2T generation problem. We extend XALIGN dataset with annotated data for four more languages: Punjabi, Malayalam, Assamese and Oriya. We conduct an extensive study using popular Transformer-based text generation models on our extended multi-lingual dataset, which we call XALIGNV2. Further, we investigate the performance of different text generation strategies: multiple variations of pretraining, fact-aware embeddings and structure-aware input encoding. Our extensive experiments show that a multi-lingual mT5 model which uses fact-aware embeddings with structure-aware input encoding leads to best results on average across the twelve languages. We make our code, dataset and model publicly available, and hope that this will help advance further research in this critical area.

The training paradigm for machine translation has gradually shifted, from learning neural machine translation (NMT) models with extensive parallel corpora to instruction finetuning on pretrained multilingual large language models (LLMs) with high-quality translation pairs. In this paper, we focus on boosting the many-to-many multilingual translation performance of LLMs with an emphasis on zero-shot translation directions. We demonstrate that prompt strategies adopted during instruction finetuning are crucial to zero-shot translation performance and introduce a cross-lingual consistency regularization, XConST, to bridge the representation gap among different languages and improve zero-shot translation performance. XConST is not a new method, but a version of CrossConST (Gao et al., 2023a) adapted for multilingual finetuning on LLMs with translation instructions. Experimental results on ALMA (Xu et al., 2023) and LLaMA-2 (Touvron et al., 2023) show that our approach consistently improves translation performance. Our implementations are available at https://github.com/gpengzhi/CrossConST-LLM.

We present X-MDPT (Cross-view Masked Diffusion Prediction Transformers), a novel diffusion model designed for pose-guided human image generation. X-MDPT distinguishes itself by employing masked diffusion transformers that operate on latent patches, a departure from the commonly-used Unet structures in existing works. The model comprises three key modules: 1) a denoising diffusion Transformer, 2) an aggregation network that consolidates conditions into a single vector for the diffusion process, and 3) a mask cross-prediction module that enhances representation learning with semantic information from the reference image. X-MDPT demonstrates scalability, improving FID, SSIM, and LPIPS with larger models. Despite its simple design, our model outperforms state-of-the-art approaches on the DeepFashion dataset while exhibiting efficiency in terms of training parameters, training time, and inference speed. Our compact 33MB model achieves an FID of 7.42, surpassing a prior Unet latent diffusion approach (FID 8.07) using only 11times fewer parameters. Our best model surpasses the pixel-based diffusion with 2{3} of the parameters and achieves 5.43 times faster inference.

Recent controllable generation approaches such as FreeControl and Diffusion Self-guidance bring fine-grained spatial and appearance control to text-to-image (T2I) diffusion models without training auxiliary modules. However, these methods optimize the latent embedding for each type of score function with longer diffusion steps, making the generation process time-consuming and limiting their flexibility and use. This work presents Ctrl-X, a simple framework for T2I diffusion controlling structure and appearance without additional training or guidance. Ctrl-X designs feed-forward structure control to enable the structure alignment with a structure image and semantic-aware appearance transfer to facilitate the appearance transfer from a user-input image. Extensive qualitative and quantitative experiments illustrate the superior performance of Ctrl-X on various condition inputs and model checkpoints. In particular, Ctrl-X supports novel structure and appearance control with arbitrary condition images of any modality, exhibits superior image quality and appearance transfer compared to existing works, and provides instant plug-and-play functionality to any T2I and text-to-video (T2V) diffusion model. See our project page for an overview of the results: https://genforce.github.io/ctrl-x

We introduce XFT, a simple yet powerful training scheme, by simply merging upcycled Mixture-of-Experts (MoE) to unleash the performance limit of instruction-tuned code Large Language Models (LLMs). While vanilla sparse upcycling fails to improve instruction tuning, XFT introduces a shared expert mechanism with a novel routing weight normalization strategy into sparse upcycling, which significantly boosts instruction tuning. After fine-tuning the upcycled MoE model, XFT introduces a learnable model merging mechanism to compile the upcycled MoE model back to a dense model, achieving upcycled MoE-level performance with only dense-model compute. By applying XFT to a 1.3B model, we create a new state-of-the-art tiny code LLM (<3B) with 67.1 and 64.6 pass@1 on HumanEval and HumanEval+ respectively. With the same data and model architecture, XFT improves supervised fine-tuning (SFT) by 13% on HumanEval+, along with consistent improvements from 2% to 13% on MBPP+, MultiPL-E, and DS-1000, demonstrating its generalizability. XFT is fully orthogonal to existing techniques such as Evol-Instruct and OSS-Instruct, opening a new dimension for improving code instruction tuning. Codes are available at https://github.com/ise-uiuc/xft .

We introduce X-Adapter, a universal upgrader to enable the pretrained plug-and-play modules (e.g., ControlNet, LoRA) to work directly with the upgraded text-to-image diffusion model (e.g., SDXL) without further retraining. We achieve this goal by training an additional network to control the frozen upgraded model with the new text-image data pairs. In detail, X-Adapter keeps a frozen copy of the old model to preserve the connectors of different plugins. Additionally, X-Adapter adds trainable mapping layers that bridge the decoders from models of different versions for feature remapping. The remapped features will be used as guidance for the upgraded model. To enhance the guidance ability of X-Adapter, we employ a null-text training strategy for the upgraded model. After training, we also introduce a two-stage denoising strategy to align the initial latents of X-Adapter and the upgraded model. Thanks to our strategies, X-Adapter demonstrates universal compatibility with various plugins and also enables plugins of different versions to work together, thereby expanding the functionalities of diffusion community. To verify the effectiveness of the proposed method, we conduct extensive experiments and the results show that X-Adapter may facilitate wider application in the upgraded foundational diffusion model.

Recent advancements in Large Language Models (LLMs) have revolutionized decision-making by breaking down complex problems into more manageable language sequences referred to as ``thoughts''. An effective thought design should consider three key perspectives: performance, efficiency, and flexibility. However, existing thought can at most exhibit two of these attributes. To address these limitations, we introduce a novel thought prompting approach called ``Everything of Thoughts'' (XoT) to defy the law of ``Penrose triangle of existing thought paradigms. XoT leverages pretrained reinforcement learning and Monte Carlo Tree Search (MCTS) to incorporate external domain knowledge into thoughts, thereby enhancing LLMs' capabilities and enabling them to generalize to unseen problems efficiently. Through the utilization of the MCTS-LLM collaborative thought revision framework, this approach autonomously produces high-quality comprehensive cognitive mappings with minimal LLM interactions. Additionally, XoT empowers LLMs to engage in unconstrained thinking, allowing for flexible cognitive mappings for problems with multiple solutions.

Optical Coherence Tomography Angiography (OCTA) and its derived en-face projections provide high-resolution visualization of the retinal and choroidal vasculature, which is critical for the rapid and accurate diagnosis of retinal diseases. However, acquiring high-quality OCTA images is challenging due to motion sensitivity and the high costs associated with software modifications for conventional OCT devices. Moreover, current deep learning methods for OCT-to-OCTA translation often overlook the vascular differences across retinal layers and struggle to reconstruct the intricate, dense vascular details necessary for reliable diagnosis. To overcome these limitations, we propose XOCT, a novel deep learning framework that integrates Cross-Dimensional Supervision (CDS) with a Multi-Scale Feature Fusion (MSFF) network for layer-aware vascular reconstruction. Our CDS module leverages 2D layer-wise en-face projections, generated via segmentation-weighted z-axis averaging, as supervisory signals to compel the network to learn distinct representations for each retinal layer through fine-grained, targeted guidance. Meanwhile, the MSFF module enhances vessel delineation through multi-scale feature extraction combined with a channel reweighting strategy, effectively capturing vascular details at multiple spatial scales. Our experiments on the OCTA-500 dataset demonstrate XOCT's improvements, especially for the en-face projections which are significant for clinical evaluation of retinal pathologies, underscoring its potential to enhance OCTA accessibility, reliability, and diagnostic value for ophthalmic disease detection and monitoring. The code is available at https://github.com/uci-cbcl/XOCT.

In the field of antibody engineering, an essential task is to design a novel antibody whose paratopes bind to a specific antigen with correct epitopes. Understanding antibody structure and its paratope can facilitate a mechanistic understanding of its function. Therefore, antibody structure prediction from its sequence alone has always been a highly valuable problem for de novo antibody design. AlphaFold2, a breakthrough in the field of structural biology, provides a solution to predict protein structure based on protein sequences and computationally expensive coevolutionary multiple sequence alignments (MSAs). However, the computational efficiency and undesirable prediction accuracy of antibodies, especially on the complementarity-determining regions (CDRs) of antibodies limit their applications in the industrially high-throughput drug design. To learn an informative representation of antibodies, we employed a deep antibody language model (ALM) on curated sequences from the observed antibody space database via a transformer model. We also developed a novel model named xTrimoABFold to predict antibody structure from antibody sequence based on the pretrained ALM as well as efficient evoformers and structural modules. The model was trained end-to-end on the antibody structures in PDB by minimizing the ensemble loss of domain-specific focal loss on CDR and the frame-aligned point loss. xTrimoABFold outperforms AlphaFold2 and other protein language model based SOTAs, e.g., OmegaFold, HelixFold-Single, and IgFold with a large significant margin (30+\% improvement on RMSD) while performing 151 times faster than AlphaFold2. To the best of our knowledge, xTrimoABFold achieved state-of-the-art antibody structure prediction. Its improvement in both accuracy and efficiency makes it a valuable tool for de novo antibody design and could make further improvements in immuno-theory.

Extreme multi-label text classification (XMTC) is the task of finding the most relevant subset labels from an extremely large-scale label collection. Recently, some deep learning models have achieved state-of-the-art results in XMTC tasks. These models commonly predict scores for all labels by a fully connected layer as the last layer of the model. However, such models can't predict a relatively complete and variable-length label subset for each document, because they select positive labels relevant to the document by a fixed threshold or take top k labels in descending order of scores. A less popular type of deep learning models called sequence-to-sequence (Seq2Seq) focus on predicting variable-length positive labels in sequence style. However, the labels in XMTC tasks are essentially an unordered set rather than an ordered sequence, the default order of labels restrains Seq2Seq models in training. To address this limitation in Seq2Seq, we propose an autoregressive sequence-to-set model for XMTC tasks named OTSeq2Set. Our model generates predictions in student-forcing scheme and is trained by a loss function based on bipartite matching which enables permutation-invariance. Meanwhile, we use the optimal transport distance as a measurement to force the model to focus on the closest labels in semantic label space. Experiments show that OTSeq2Set outperforms other competitive baselines on 4 benchmark datasets. Especially, on the Wikipedia dataset with 31k labels, it outperforms the state-of-the-art Seq2Seq method by 16.34% in micro-F1 score. The code is available at https://github.com/caojie54/OTSeq2Set.

Multimodal pre-training with text, layout, and image has achieved SOTA performance for visually-rich document understanding tasks recently, which demonstrates the great potential for joint learning across different modalities. In this paper, we present LayoutXLM, a multimodal pre-trained model for multilingual document understanding, which aims to bridge the language barriers for visually-rich document understanding. To accurately evaluate LayoutXLM, we also introduce a multilingual form understanding benchmark dataset named XFUND, which includes form understanding samples in 7 languages (Chinese, Japanese, Spanish, French, Italian, German, Portuguese), and key-value pairs are manually labeled for each language. Experiment results show that the LayoutXLM model has significantly outperformed the existing SOTA cross-lingual pre-trained models on the XFUND dataset. The pre-trained LayoutXLM model and the XFUND dataset are publicly available at https://aka.ms/layoutxlm.

In this work, we present Xwin-LM, a comprehensive suite of alignment methodologies for large language models (LLMs). This suite encompasses several key techniques, including supervised finetuning (SFT), reward modeling (RM), rejection sampling finetuning (RS), and direct preference optimization (DPO). The key components are as follows: (1) Xwin-LM-SFT, models initially finetuned with high-quality instruction data; (2) Xwin-Pair, a large-scale, multi-turn preference dataset meticulously annotated using GPT-4; (3) Xwin-RM, reward models trained on Xwin-Pair, developed at scales of 7B, 13B, and 70B parameters; (4) Xwin-Set, a multiwise preference dataset in which each prompt is linked to 64 unique responses generated by Xwin-LM-SFT and scored by Xwin-RM; (5) Xwin-LM-RS, models finetuned with the highest-scoring responses from Xwin-Set; (6) Xwin-LM-DPO, models further optimized on Xwin-Set using the DPO algorithm. Our evaluations on AlpacaEval and MT-bench demonstrate consistent and significant improvements across the pipeline, demonstrating the strength and scalability of Xwin-LM. The repository https://github.com/Xwin-LM/Xwin-LM will be continually updated to foster community research.

Transformers have achieved great success in many artificial intelligence fields, such as natural language processing, computer vision, and audio processing. Therefore, it is natural to attract lots of interest from academic and industry researchers. Up to the present, a great variety of Transformer variants (a.k.a. X-formers) have been proposed, however, a systematic and comprehensive literature review on these Transformer variants is still missing. In this survey, we provide a comprehensive review of various X-formers. We first briefly introduce the vanilla Transformer and then propose a new taxonomy of X-formers. Next, we introduce the various X-formers from three perspectives: architectural modification, pre-training, and applications. Finally, we outline some potential directions for future research.

The surge of pre-training has witnessed the rapid development of document understanding recently. Pre-training and fine-tuning framework has been effectively used to tackle texts in various formats, including plain texts, document texts, and web texts. Despite achieving promising performance, existing pre-trained models usually target one specific document format at one time, making it difficult to combine knowledge from multiple document formats. To address this, we propose XDoc, a unified pre-trained model which deals with different document formats in a single model. For parameter efficiency, we share backbone parameters for different formats such as the word embedding layer and the Transformer layers. Meanwhile, we introduce adaptive layers with lightweight parameters to enhance the distinction across different formats. Experimental results have demonstrated that with only 36.7% parameters, XDoc achieves comparable or even better performance on a variety of downstream tasks compared with the individual pre-trained models, which is cost effective for real-world deployment. The code and pre-trained models will be publicly available at https://aka.ms/xdoc.

Large Language Models (LLMs) have become ubiquitous across various domains, transforming the way we interact with information and conduct research. However, most high-performing LLMs remain confined behind proprietary walls, hindering scientific progress. Most open-source LLMs, on the other hand, are limited in their ability to support longer sequence lengths, which is a key requirement for many tasks that require inference over an input context. To address this, we have trained XGen, a series of 7B parameter models on up to 8K sequence length for up to 1.5T tokens. We have also finetuned the XGen models on public-domain instructional data, creating their instruction-tuned counterparts (XGen-Inst). We open-source our models for both research advancements and commercial applications. Our evaluation on standard benchmarks shows that XGen models achieve comparable or better results when compared with state-of-the-art open-source LLMs. Our targeted evaluation on long sequence modeling tasks shows the benefits of our 8K-sequence models over 2K-sequence open-source LLMs.

Multiple Sequence Alignment (MSA) plays a pivotal role in unveiling the evolutionary trajectories of protein families. The accuracy of protein structure predictions is often compromised for protein sequences that lack sufficient homologous information to construct high quality MSA. Although various methods have been proposed to generate virtual MSA under these conditions, they fall short in comprehensively capturing the intricate coevolutionary patterns within MSA or require guidance from external oracle models. Here we introduce MSAGPT, a novel approach to prompt protein structure predictions via MSA generative pretraining in the low MSA regime. MSAGPT employs a simple yet effective 2D evolutionary positional encoding scheme to model complex evolutionary patterns. Endowed by this, its flexible 1D MSA decoding framework facilitates zero or few shot learning. Moreover, we demonstrate that leveraging the feedback from AlphaFold2 can further enhance the model capacity via Rejective Fine tuning (RFT) and Reinforcement Learning from AF2 Feedback (RLAF). Extensive experiments confirm the efficacy of MSAGPT in generating faithful virtual MSA to enhance the structure prediction accuracy. The transfer learning capabilities also highlight its great potential for facilitating other protein tasks.

While many BERT-based cross-modal pre-trained models produce excellent results on downstream understanding tasks like image-text retrieval and VQA, they cannot be applied to generation tasks directly. In this paper, we propose XGPT, a new method of Cross-modal Generative Pre-Training for Image Captioning that is designed to pre-train text-to-image caption generators through three novel generation tasks, including Image-conditioned Masked Language Modeling (IMLM), Image-conditioned Denoising Autoencoding (IDA), and Text-conditioned Image Feature Generation (TIFG). As a result, the pre-trained XGPT can be fine-tuned without any task-specific architecture modifications to create state-of-the-art models for image captioning. Experiments show that XGPT obtains new state-of-the-art results on the benchmark datasets, including COCO Captions and Flickr30k Captions. We also use XGPT to generate new image captions as data augmentation for the image retrieval task and achieve significant improvement on all recall metrics.

While machine translation (MT) systems are achieving increasingly strong performance on benchmarks, they often produce translations with errors and anomalies. Understanding these errors can potentially help improve the translation quality and user experience. This paper introduces xTower, an open large language model (LLM) built on top of TowerBase designed to provide free-text explanations for translation errors in order to guide the generation of a corrected translation. The quality of the generated explanations by xTower are assessed via both intrinsic and extrinsic evaluation. We ask expert translators to evaluate the quality of the explanations across two dimensions: relatedness towards the error span being explained and helpfulness in error understanding and improving translation quality. Extrinsically, we test xTower across various experimental setups in generating translation corrections, demonstrating significant improvements in translation quality. Our findings highlight xTower's potential towards not only producing plausible and helpful explanations of automatic translations, but also leveraging them to suggest corrected translations.

Despite the power of Large Language Models (LLMs) like GPT-4, they still struggle with tasks that require generating complex, structured outputs. In this study, we assess the capability of Current LLMs in generating complex structured data and propose a structure-aware fine-tuning approach as a solution to improve this ability. To perform a comprehensive evaluation, we propose Struc-Bench, include five representative LLMs (i.e., GPT-NeoX 20B, GPT-3.5, GPT-4, and Vicuna) and evaluate them on our carefully constructed datasets spanning raw text, HTML, and LaTeX tables. Based on our analysis of current model performance, we identify specific common formatting errors and areas of potential improvement. To address complex formatting requirements, we utilize FormatCoT (Chain-of-Thought) to generate format instructions from target outputs. Our experiments show that our structure-aware fine-tuning method, when applied to LLaMA-7B, significantly improves adherence to natural language constraints, outperforming other evaluated LLMs. Based on these results, we present an ability map of model capabilities from six dimensions (i.e., coverage, formatting, reasoning, comprehension, pragmatics, and hallucination). This map highlights the weaknesses of LLMs in handling complex structured outputs and suggests promising directions for future work. Our code and models can be found at https://github.com/gersteinlab/Struc-Bench.

Multiple critical scenarios (like Wikipedia text generation given English Infoboxes) need automated generation of descriptive text in low resource (LR) languages from English fact triples. Previous work has focused on English fact-to-text (F2T) generation. To the best of our knowledge, there has been no previous attempt on cross-lingual alignment or generation for LR languages. Building an effective cross-lingual F2T (XF2T) system requires alignment between English structured facts and LR sentences. We propose two unsupervised methods for cross-lingual alignment. We contribute XALIGN, an XF2T dataset with 0.45M pairs across 8 languages, of which 5402 pairs have been manually annotated. We also train strong baseline XF2T generation models on the XAlign dataset.

We introduce a new proxy score for evaluating bitext mining based on similarity in a multilingual embedding space: xSIM++. In comparison to xSIM, this improved proxy leverages rule-based approaches to extend English sentences in any evaluation set with synthetic, hard-to-distinguish examples which more closely mirror the scenarios we encounter during large-scale mining. We validate this proxy by running a significant number of bitext mining experiments for a set of low-resource languages, and subsequently train NMT systems on the mined data. In comparison to xSIM, we show that xSIM++ is better correlated with the downstream BLEU scores of translation systems trained on mined bitexts, providing a reliable proxy of bitext mining performance without needing to run expensive bitext mining pipelines. xSIM++ also reports performance for different error types, offering more fine-grained feedback for model development.

State-of-the-art trainable machine translation evaluation metrics like xCOMET achieve high correlation with human judgment but rely on large encoders (up to 10.7B parameters), making them computationally expensive and inaccessible to researchers with limited resources. To address this issue, we investigate whether the knowledge stored in these large encoders can be compressed while maintaining quality. We employ distillation, quantization, and pruning techniques to create efficient xCOMET alternatives and introduce a novel data collection pipeline for efficient black-box distillation. Our experiments show that, using quantization, xCOMET can be compressed up to three times with no quality degradation. Additionally, through distillation, we create an xCOMET-lite metric, which has only 2.6% of xCOMET-XXL parameters, but retains 92.1% of its quality. Besides, it surpasses strong small-scale metrics like COMET-22 and BLEURT-20 on the WMT22 metrics challenge dataset by 6.4%, despite using 50% fewer parameters. All code, dataset, and models are available online.

We propose LGGPT, an LLM-based model tailored for unified layout generation. First, we propose Arbitrary Layout Instruction (ALI) and Universal Layout Response (ULR) as the uniform I/O template. ALI accommodates arbitrary layout generation task inputs across multiple layout domains, enabling LGGPT to unify both task-generic and domain-generic layout generation hitherto unexplored. Collectively, ALI and ULR boast a succinct structure that forgoes superfluous tokens typically found in existing HTML-based formats, facilitating efficient instruction tuning and boosting unified generation performance. In addition, we propose an Interval Quantization Encoding (IQE) strategy that compresses ALI into a more condensed structure. IQE precisely preserves valid layout clues while eliminating the less informative placeholders, facilitating LGGPT to capture complex and variable layout generation conditions during the unified training process. Experimental results demonstrate that LGGPT achieves superior or on par performance compared to existing methods. Notably, LGGPT strikes a prominent balance between proficiency and efficiency with a compact 1.5B parameter LLM, which beats prior 7B or 175B models even in the most extensive and challenging unified scenario. Furthermore, we underscore the necessity of employing LLMs for unified layout generation and suggest that 1.5B could be an optimal parameter size by comparing LLMs of varying scales. Code is available at https://github.com/NiceRingNode/LGGPT.

Inferring causal structure poses a combinatorial search problem that typically involves evaluating structures with a score or independence test. The resulting search is costly, and designing suitable scores or tests that capture prior knowledge is difficult. In this work, we propose to amortize causal structure learning. Rather than searching over structures, we train a variational inference model to directly predict the causal structure from observational or interventional data. This allows our inference model to acquire domain-specific inductive biases for causal discovery solely from data generated by a simulator, bypassing both the hand-engineering of suitable score functions and the search over graphs. The architecture of our inference model emulates permutation invariances that are crucial for statistical efficiency in structure learning, which facilitates generalization to significantly larger problem instances than seen during training. On synthetic data and semisynthetic gene expression data, our models exhibit robust generalization capabilities when subject to substantial distribution shifts and significantly outperform existing algorithms, especially in the challenging genomics domain. Our code and models are publicly available at: https://github.com/larslorch/avici.

The adaptation of large language models (LLMs) to chemistry has shown promising performance in molecular understanding tasks, such as generating a text description from a molecule. However, proper reasoning based on molecular structural information remains a significant challenge, e.g., even advanced LLMs such as GPT-4o struggle to identify functional groups which are crucial for inferring the molecular property of interest. To address this limitation, we propose StructCoT, a structure-aware chain-of-thought (CoT) that enhances LLMs' understanding of molecular structures by explicitly injecting the key structural features of molecules. Moreover, we introduce two fine-tuning frameworks for adapting the existing LLMs to use our StructCoT. Our experiments demonstrate that incorporating StructCoT with our fine-tuning frameworks leads to consistent improvements in both molecular understanding tasks.

Tabular data -- structured, heterogeneous, spreadsheet-style data with rows and columns -- is widely used in practice across many domains. However, while recent foundation models have reduced the need for developing task-specific datasets and predictors in domains such as language modeling and computer vision, this transfer learning paradigm has not had similar impact in the tabular domain. In this work, we seek to narrow this gap and present TabuLa-8B, a language model for tabular prediction. We define a process for extracting a large, high-quality training dataset from the TabLib corpus, proposing methods for tabular data filtering and quality control. Using the resulting dataset, which comprises over 1.6B rows from 3.1M unique tables, we fine-tune a Llama 3-8B large language model (LLM) for tabular data prediction (classification and binned regression) using a novel packing and attention scheme for tabular prediction. Through evaluation across a test suite of 329 datasets, we find that TabuLa-8B has zero-shot accuracy on unseen tables that is over 15 percentage points (pp) higher than random guessing, a feat that is not possible with existing state-of-the-art tabular prediction models (e.g. XGBoost, TabPFN). In the few-shot setting (1-32 shots), without any fine-tuning on the target datasets, TabuLa-8B is 5-15 pp more accurate than XGBoost and TabPFN models that are explicitly trained on equal, or even up to 16x more data. We release our model, code, and data along with the publication of this paper.

Protein language models have shown remarkable success in learning biological information from protein sequences. However, most existing models are limited by either autoencoding or autoregressive pre-training objectives, which makes them struggle to handle protein understanding and generation tasks concurrently. We propose a unified protein language model, xTrimoPGLM, to address these two types of tasks simultaneously through an innovative pre-training framework. Our key technical contribution is an exploration of the compatibility and the potential for joint optimization of the two types of objectives, which has led to a strategy for training xTrimoPGLM at an unprecedented scale of 100 billion parameters and 1 trillion training tokens. Our extensive experiments reveal that 1) xTrimoPGLM significantly outperforms other advanced baselines in 18 protein understanding benchmarks across four categories. The model also facilitates an atomic-resolution view of protein structures, leading to an advanced 3D structural prediction model that surpasses existing language model-based tools. 2) xTrimoPGLM not only can generate de novo protein sequences following the principles of natural ones, but also can perform programmable generation after supervised fine-tuning (SFT) on curated sequences. These results highlight the substantial capability and versatility of xTrimoPGLM in understanding and generating protein sequences, contributing to the evolving landscape of foundation models in protein science.

Table Structure Recognition (TSR) is vital for various downstream tasks like information retrieval, table reconstruction, and document understanding. While most state-of-the-art (SOTA) research predominantly focuses on TSR in English documents, the need for similar capabilities in other languages is evident, considering the global diversity of data. Moreover, creating substantial labeled data in non-English languages and training these SOTA models from scratch is costly and time-consuming. We propose TSR as a language-agnostic cell arrangement prediction and introduce SPRINT, Script-agnostic Structure Recognition in Tables. SPRINT uses recently introduced Optimized Table Structure Language (OTSL) sequences to predict table structures. We show that when coupled with a pre-trained table grid estimator, SPRINT can improve the overall tree edit distance-based similarity structure scores of tables even for non-English documents. We experimentally evaluate our performance across benchmark TSR datasets including PubTabNet, FinTabNet, and PubTables-1M. Our findings reveal that SPRINT not only matches SOTA models in performance on standard datasets but also demonstrates lower latency. Additionally, SPRINT excels in accurately identifying table structures in non-English documents, surpassing current leading models by showing an absolute average increase of 11.12%. We also present an algorithm for converting valid OTSL predictions into a widely used HTML-based table representation. To encourage further research, we release our code and Multilingual Scanned and Scene Table Structure Recognition Dataset, MUSTARD labeled with OTSL sequences for 1428 tables in thirteen languages encompassing several scripts at https://github.com/IITB-LEAP-OCR/SPRINT

Structured Natural Language Processing (XNLP) is an important subset of NLP that entails understanding the underlying semantic or syntactic structure of texts, which serves as a foundational component for many downstream applications. Despite certain recent efforts to explore universal solutions for specific categories of XNLP tasks, a comprehensive and effective approach for unifying all XNLP tasks long remains underdeveloped. In the meanwhile, while XNLP demonstration systems are vital for researchers exploring various XNLP tasks, existing platforms can be limited to, e.g., supporting few XNLP tasks, lacking interactivity and universalness. To this end, we propose an advanced XNLP demonstration platform, where we propose leveraging LLM to achieve universal XNLP, with one model for all with high generalizability. Overall, our system advances in multiple aspects, including universal XNLP modeling, high performance, interpretability, scalability, and interactivity, providing a unified platform for exploring diverse XNLP tasks in the community. XNLP is online: https://xnlp.haofei.vip

Recent works on structured text translation remain limited to the sentence level, as they struggle to effectively handle the complex document-level XML or HTML structures. To address this, we propose Format Reinforcement Learning (FormatRL), which employs Group Relative Policy Optimization on top of a supervised fine-tuning model to directly optimize novel structure-aware rewards: 1) TreeSim, which measures structural similarity between predicted and reference XML trees and 2) Node-chrF, which measures translation quality at the level of XML nodes. Additionally, we apply StrucAUC, a fine-grained metric distinguishing between minor errors and major structural failures. Experiments on the SAP software-documentation benchmark demonstrate improvements across six metrics and an analysis further shows how different reward functions contribute to improvements in both structural and translation quality.

Despite the growing adoption of large language models (LLMs) in academic workflows, their capabilities remain limited when it comes to supporting high-quality scientific writing. Most existing systems are designed for general-purpose scientific text generation and fail to meet the sophisticated demands of research communication beyond surface-level polishing, such as conceptual coherence across sections. Furthermore, academic writing is inherently iterative and revision-driven, a process not well supported by direct prompting-based paradigms. To address these scenarios, we propose a human-AI collaboration framework for academic paper revision. We first introduce a comprehensive dataset of 7,040 research papers from top-tier venues annotated with over 140,000 instruction-response pairs that reflect realistic, section-level scientific revisions. Building on the dataset, we develop XtraGPT, the first suite of open-source LLMs, designed to provide context-aware, instruction-guided writing assistance, ranging from 1.5B to 14B parameters. Extensive experiments validate that XtraGPT significantly outperforms same-scale baselines and approaches the quality of proprietary systems. Both automated preference assessments and human evaluations confirm the effectiveness of our models in improving scientific drafts.

We introduce the latest series of TeleChat models: TeleChat2, TeleChat2.5, and T1, offering a significant upgrade over their predecessor, TeleChat. Despite minimal changes to the model architecture, the new series achieves substantial performance gains through enhanced training strategies in both pre-training and post-training stages. The series begins with TeleChat2, which undergoes pretraining on 10 trillion high-quality and diverse tokens. This is followed by Supervised Fine-Tuning (SFT) and Direct Preference Optimization (DPO) to further enhance its capabilities. TeleChat2.5 and T1 expand the pipeline by incorporating a continual pretraining phase with domain-specific datasets, combined with reinforcement learning (RL) to improve performance in code generation and mathematical reasoning tasks. The T1 variant is designed for complex reasoning, supporting long Chain-of-Thought (CoT) reasoning and demonstrating substantial improvements in mathematics and coding. In contrast, TeleChat2.5 prioritizes speed, delivering rapid inference. Both flagship models of T1 and TeleChat2.5 are dense Transformer-based architectures with 115B parameters, showcasing significant advancements in reasoning and general task performance compared to the original TeleChat. Notably, T1-115B outperform proprietary models such as OpenAI's o1-mini and GPT-4o. We publicly release TeleChat2, TeleChat2.5 and T1, including post-trained versions with 35B and 115B parameters, to empower developers and researchers with state-of-the-art language models tailored for diverse applications.

Parameter-efficient fine-tuning (PEFT) for cross-task generalization consists in pre-training adapters on a multi-task training set before few-shot adaptation to test tasks. Polytropon [Ponti et al., 2023] (Poly) jointly learns an inventory of adapters and a routing function that selects a (variable-size) subset of adapters for each task during both pre-training and few-shot adaptation. In this paper, we investigate the role that adapter routing plays in its success and design new variants based on our findings. First, we build on the intuition that finer-grained routing provides more expressivity. Hence, we propose MHR (Multi-Head Routing), which combines subsets of adapter parameters and outperforms Poly under a comparable parameter budget; by only fine-tuning the routing function and not the adapters (MHR-z), we achieve competitive performance with extreme parameter efficiency. Second, we find that Poly/MHR performance is a result of better multi-task optimization, rather than modular inductive biases that facilitate adapter recombination and local adaptation, as previously hypothesized. In fact, we find that MHR exhibits higher gradient alignment between tasks than any other method. Since this implies that routing is only crucial during multi-task pre-training, we propose MHR-mu, which discards routing and fine-tunes the average of the pre-trained adapters during few-shot adaptation. This establishes MHR-mu as an effective method for single-adapter fine-tuning.

This report introduces xGen-MM (also known as BLIP-3), a framework for developing Large Multimodal Models (LMMs). The framework comprises meticulously curated datasets, a training recipe, model architectures, and a resulting suite of LMMs. xGen-MM, short for xGen-MultiModal, expands the Salesforce xGen initiative on foundation AI models. Our models undergo rigorous evaluation across a range of tasks, including both single and multi-image benchmarks. Our pre-trained base model exhibits strong in-context learning capabilities and the instruction-tuned model demonstrates competitive performance among open-source LMMs with similar model sizes. In addition, we introduce a safety-tuned model with DPO, aiming to mitigate harmful behaviors such as hallucinations and improve safety. We open-source our models, curated large-scale datasets, and our fine-tuning codebase to facilitate further advancements in LMM research. Associated resources will be available on our project page above.

Lung diseases remain a critical global health concern, and it's crucial to have accurate and quick ways to diagnose them. This work focuses on classifying different lung diseases into five groups: viral pneumonia, bacterial pneumonia, COVID, tuberculosis, and normal lungs. Employing advanced deep learning techniques, we explore a diverse range of models including CNN, hybrid models, ensembles, transformers, and Big Transfer. The research encompasses comprehensive methodologies such as hyperparameter tuning, stratified k-fold cross-validation, and transfer learning with fine-tuning.Remarkably, our findings reveal that the Xception model, fine-tuned through 5-fold cross-validation, achieves the highest accuracy of 96.21\%. This success shows that our methods work well in accurately identifying different lung diseases. The exploration of explainable artificial intelligence (XAI) methodologies further enhances our understanding of the decision-making processes employed by these models, contributing to increased trust in their clinical applications.

Chain-of-thought (CoT) has emerged as a powerful technique to elicit reasoning in large language models and improve a variety of downstream tasks. CoT mainly demonstrates excellent performance in English, but its usage in low-resource languages is constrained due to poor language generalization. To bridge the gap among different languages, we propose a cross-lingual instruction fine-tuning framework (xCOT) to transfer knowledge from high-resource languages to low-resource languages. Specifically, the multilingual instruction training data (xCOT-INSTRUCT) is created to encourage the semantic alignment of multiple languages. We introduce cross-lingual in-context few-shot learning (xICL)) to accelerate multilingual agreement in instruction tuning, where some fragments of source languages in examples are randomly substituted by their counterpart translations of target languages. During multilingual instruction tuning, we adopt the randomly online CoT strategy to enhance the multilingual reasoning ability of the large language model by first translating the query to another language and then answering in English. To further facilitate the language transfer, we leverage the high-resource CoT to supervise the training of low-resource languages with cross-lingual distillation. Experimental results on previous benchmarks demonstrate the superior performance of xCoT in reducing the gap among different languages, highlighting its potential to reduce the cross-lingual gap.

Tensor network (TN) is a powerful framework in machine learning, but selecting a good TN model, known as TN structure search (TN-SS), is a challenging and computationally intensive task. The recent approach TNLS~li2022permutation showed promising results for this task, however, its computational efficiency is still unaffordable, requiring too many evaluations of the objective function. We propose TnALE, a new algorithm that updates each structure-related variable alternately by local enumeration, greatly reducing the number of evaluations compared to TNLS. We theoretically investigate the descent steps for TNLS and TnALE, proving that both algorithms can achieve linear convergence up to a constant if a sufficient reduction of the objective is reached in each neighborhood. We also compare the evaluation efficiency of TNLS and TnALE, revealing that Omega(2^N) evaluations are typically required in TNLS for reaching the objective reduction in the neighborhood, while ideally O(N^2R) evaluations are sufficient in TnALE, where N denotes the tensor order and R reflects the ``low-rankness'' of the neighborhood. Experimental results verify that TnALE can find practically good TN-ranks and permutations with vastly fewer evaluations than the state-of-the-art algorithms.

Text editing is a crucial task that involves modifying text to better align with user intents. However, existing text editing benchmark datasets have limitations in providing only coarse-grained instructions. Consequently, although the edited output may seem reasonable, it often deviates from the intended changes outlined in the gold reference, resulting in low evaluation scores. To comprehensively investigate the text editing capabilities of large language models, this paper introduces XATU, the first benchmark specifically designed for fine-grained instruction-based explainable text editing. XATU covers a wide range of topics and text types, incorporating lexical, syntactic, semantic, and knowledge-intensive edits. To enhance interpretability, we leverage high-quality data sources and human annotation, resulting in a benchmark that includes fine-grained instructions and gold-standard edit explanations. By evaluating existing open and closed large language models against our benchmark, we demonstrate the effectiveness of instruction tuning and the impact of underlying architecture across various editing tasks. Furthermore, extensive experimentation reveals the significant role of explanations in fine-tuning language models for text editing tasks. The benchmark will be open-sourced to support reproduction and facilitate future research.

The softmax (also called softargmax) function is widely used in machine learning models to normalize real-valued scores into a probability distribution. To avoid floating-point overflow, the softmax function is conventionally implemented in three passes: the first pass to compute the normalization constant, and two other passes to compute outputs from normalized inputs. We analyze two variants of the Three-Pass algorithm and demonstrate that in a well-optimized implementation on HPC-class processors performance of all three passes is limited by memory bandwidth. We then present a novel algorithm for softmax computation in just two passes. The proposed Two-Pass algorithm avoids both numerical overflow and the extra normalization pass by employing an exotic representation for intermediate values, where each value is represented as a pair of floating-point numbers: one representing the "mantissa" and another representing the "exponent". Performance evaluation demonstrates that on out-of-cache inputs on an Intel Skylake-X processor the new Two-Pass algorithm outperforms the traditional Three-Pass algorithm by up to 28% in AVX512 implementation, and by up to 18% in AVX2 implementation. The proposed Two-Pass algorithm also outperforms the traditional Three-Pass algorithm on Intel Broadwell and AMD Zen 2 processors. To foster reproducibility, we released an open-source implementation of the new Two-Pass Softmax algorithm and other experiments in this paper as a part of XNNPACK library at GitHub.com/google/XNNPACK.

Language models demonstrate fundamental abilities in syntax, semantics, and reasoning, though their performance often depends significantly on the inputs they process. This study introduces TSIS (Simplified TSID) and its variants:TSISD (TSIS with Depth-First Search), TSISO (TSIS in Order), and TSISR (TSIS in Random), as integral components of the t-SMILES framework. These additions complete the framework's design, providing diverse approaches to molecular representation. Through comprehensive analysis and experiments employing deep generative models, including GPT, diffusion models, and reinforcement learning, the findings reveal that the hierarchical structure of t-SMILES is more straightforward to parse than initially anticipated. Furthermore, t-SMILES consistently outperforms other linear representations such as SMILES, SELFIES, and SAFE, demonstrating superior convergence speed and enhanced generalization capabilities.

We take the first step towards multilingual style transfer by creating and releasing XFORMAL, a benchmark of multiple formal reformulations of informal text in Brazilian Portuguese, French, and Italian. Results on XFORMAL suggest that state-of-the-art style transfer approaches perform close to simple baselines, indicating that style transfer is even more challenging when moving multilingual.

Previous studies have shown that automated text-mining tools are becoming increasingly important for successfully unlocking variant information in scientific literature at large scale. Despite multiple attempts in the past, existing tools are still of limited recognition scope and precision. We propose tmVar 3.0: an improved variant recognition and normalization tool. Compared to its predecessors, tmVar 3.0 is able to recognize a wide spectrum of variant related entities (e.g., allele and copy number variants), and to group different variant mentions belonging to the same concept in an article for improved accuracy. Moreover, tmVar3 provides additional variant normalization options such as allele-specific identifiers from the ClinGen Allele Registry. tmVar3 exhibits a state-of-the-art performance with over 90% accuracy in F-measure in variant recognition and normalization, when evaluated on three independent benchmarking datasets. tmVar3 is freely available for download. We have also processed the entire PubMed and PMC with tmVar3 and released its annotations on our FTP. Availability: ftp://ftp.ncbi.nlm.nih.gov/pub/lu/tmVar3

The training of large language models (LLMs) necessitates substantial data and computational resources, and updating outdated LLMs entails significant efforts and resources. While numerous model editing techniques (METs) have emerged to efficiently update model outputs without retraining, their effectiveness in multilingual LLMs, where knowledge is stored in diverse languages, remains an underexplored research area. This research paper introduces the cross-lingual model editing (XME) paradigm, wherein a fact is edited in one language, and the subsequent update propagation is observed across other languages. To investigate the XME paradigm, we conducted experiments using BLOOM, mBERT, and XLM-RoBERTa using the two writing scripts: Latin (English, French, and Spanish) and Indic (Hindi, Gujarati, and Bengali). The results reveal notable performance limitations of state-of-the-art METs under the XME setting, mainly when the languages involved belong to two distinct script families. These findings highlight the need for further research and development of XME techniques to address these challenges. For more comprehensive information, the dataset used in this research and the associated code are publicly available at the following URLhttps://github.com/lingo-iitgn/XME.

Protein language models are a powerful tool for learning protein representations through pre-training on vast protein sequence datasets. However, traditional protein language models lack explicit structural supervision, despite its relevance to protein function. To address this issue, we introduce the integration of remote homology detection to distill structural information into protein language models without requiring explicit protein structures as input. We evaluate the impact of this structure-informed training on downstream protein function prediction tasks. Experimental results reveal consistent improvements in function annotation accuracy for EC number and GO term prediction. Performance on mutant datasets, however, varies based on the relationship between targeted properties and protein structures. This underscores the importance of considering this relationship when applying structure-aware training to protein function prediction tasks. Code and model weights are available at https://github.com/DeepGraphLearning/esm-s.

The success of self-supervised learning in computer vision and natural language processing has motivated pretraining methods on tabular data. However, most existing tabular self-supervised learning models fail to leverage information across multiple data tables and cannot generalize to new tables. In this work, we introduce XTab, a framework for cross-table pretraining of tabular transformers on datasets from various domains. We address the challenge of inconsistent column types and quantities among tables by utilizing independent featurizers and using federated learning to pretrain the shared component. Tested on 84 tabular prediction tasks from the OpenML-AutoML Benchmark (AMLB), we show that (1) XTab consistently boosts the generalizability, learning speed, and performance of multiple tabular transformers, (2) by pretraining FT-Transformer via XTab, we achieve superior performance than other state-of-the-art tabular deep learning models on various tasks such as regression, binary, and multiclass classification.

In this paper, we introduce XGLUE, a new benchmark dataset that can be used to train large-scale cross-lingual pre-trained models using multilingual and bilingual corpora and evaluate their performance across a diverse set of cross-lingual tasks. Comparing to GLUE(Wang et al., 2019), which is labeled in English for natural language understanding tasks only, XGLUE has two main advantages: (1) it provides 11 diversified tasks that cover both natural language understanding and generation scenarios; (2) for each task, it provides labeled data in multiple languages. We extend a recent cross-lingual pre-trained model Unicoder(Huang et al., 2019) to cover both understanding and generation tasks, which is evaluated on XGLUE as a strong baseline. We also evaluate the base versions (12-layer) of Multilingual BERT, XLM and XLM-R for comparison.

Aligning foundation models is essential for their safe and trustworthy deployment. However, traditional fine-tuning methods are computationally intensive and require updating billions of model parameters. A promising alternative, alignment via decoding, adjusts the response distribution directly without model updates to maximize a target reward r, thus providing a lightweight and adaptable framework for alignment. However, principled decoding methods rely on oracle access to an optimal Q-function (Q^*), which is often unavailable in practice. Hence, prior SoTA methods either approximate this Q^* using Q^{pi_{sft}} (derived from the reference SFT model) or rely on short-term rewards, resulting in sub-optimal decoding performance. In this work, we propose Transfer Q^*, which implicitly estimates the optimal value function for a target reward r through a baseline model rho_{BL} aligned with a baseline reward rho_{BL} (which can be different from the target reward r). Theoretical analyses of Transfer Q^* provide a rigorous characterization of its optimality, deriving an upper bound on the sub-optimality gap and identifying a hyperparameter to control the deviation from the pre-trained reference SFT model based on user needs. Our approach significantly reduces the sub-optimality gap observed in prior SoTA methods and demonstrates superior empirical performance across key metrics such as coherence, diversity, and quality in extensive tests on several synthetic and real datasets.

Multiple sequence alignments (MSAs) of proteins encode rich biological information and have been workhorses in bioinformatic methods for tasks like protein design and protein structure prediction for decades. Recent breakthroughs like AlphaFold2 that use transformers to attend directly over large quantities of raw MSAs have reaffirmed their importance. Generation of MSAs is highly computationally intensive, however, and no datasets comparable to those used to train AlphaFold2 have been made available to the research community, hindering progress in machine learning for proteins. To remedy this problem, we introduce OpenProteinSet, an open-source corpus of more than 16 million MSAs, associated structural homologs from the Protein Data Bank, and AlphaFold2 protein structure predictions. We have previously demonstrated the utility of OpenProteinSet by successfully retraining AlphaFold2 on it. We expect OpenProteinSet to be broadly useful as training and validation data for 1) diverse tasks focused on protein structure, function, and design and 2) large-scale multimodal machine learning research.

Protein representation learning (PRL) is crucial for understanding structure-function relationships, yet current sequence- and graph-based methods fail to capture the hierarchical organization inherent in protein structures. We introduce Topotein, a comprehensive framework that applies topological deep learning to PRL through the novel Protein Combinatorial Complex (PCC) and Topology-Complete Perceptron Network (TCPNet). Our PCC represents proteins at multiple hierarchical levels -- from residues to secondary structures to complete proteins -- while preserving geometric information at each level. TCPNet employs SE(3)-equivariant message passing across these hierarchical structures, enabling more effective capture of multi-scale structural patterns. Through extensive experiments on four PRL tasks, TCPNet consistently outperforms state-of-the-art geometric graph neural networks. Our approach demonstrates particular strength in tasks such as fold classification which require understanding of secondary structure arrangements, validating the importance of hierarchical topological features for protein analysis.

The emergence of Large Language Models (LLMs) has advanced the multilingual machine translation (MMT), yet the Curse of Multilinguality (CoM) remains a major challenge. Existing work in LLM-based MMT typically mitigates this issue via scaling up training and computation budget, which raises a critical question: Is scaling up the training and computation budget truly necessary for high-quality MMT, or can a deeper understanding of CoM provide a more efficient solution? To explore this problem, we analyze the linguistic conflicts and synergy, the underlying mechanism of CoM during post-training phase. We identify an asymmetric phenomenon in linguistic conflicts and synergy: the dominance of conflicts and synergy varies in different translation directions, leading to sub-optimal adaptation in existing post-training methods. We further find that a significant bottleneck in MMT appears to lie in post-training rather than multilingual pre-training, suggesting the need for more effective adaptation strategies. Building on these new insights, we propose a direction-aware training approach, combined with group-wise model merging, to address asymmetry in linguistic conflicts and synergy explicitly. Leveraging this strategy, our method fine-tunes X-ALMA-13B-Pretrain-trained only with multilingual pre-training-achieving comparable performance to XALMA-13B (only SFT) while using only 20B pretraining tokens and 17B parameters-5.5x fewer pretraining-tokens and 1.7x fewer model size-with just 0.85 COMET drop on Flores-200 testsets of 50 languages.

Related works used indexes like CKA and variants of CCA to measure the similarity of cross-lingual representations in multilingual language models. In this paper, we argue that assumptions of CKA/CCA align poorly with one of the motivating goals of cross-lingual learning analysis, i.e., explaining zero-shot cross-lingual transfer. We highlight what valuable aspects of cross-lingual similarity these indexes fail to capture and provide a motivating case study demonstrating the problem empirically. Then, we introduce Average Neuron-Wise Correlation (ANC) as a straightforward alternative that is exempt from the difficulties of CKA/CCA and is good specifically in a cross-lingual context. Finally, we use ANC to construct evidence that the previously introduced ``first align, then predict'' pattern takes place not only in masked language models (MLMs) but also in multilingual models with causal language modeling objectives (CLMs). Moreover, we show that the pattern extends to the scaled versions of the MLMs and CLMs (up to 85x original mBERT).Our code is publicly available at \url{https://github.com/TartuNLP/xsim}

The alignment between RNA sequences and structures in foundation models (FMs) has yet to be thoroughly investigated. Existing FMs have struggled to establish sequence-structure alignment, hindering the free flow of genomic information between RNA sequences and structures. In this study, we introduce OmniGenome, an RNA FM trained to align RNA sequences with respect to secondary structures based on structure-contextualised modelling. The alignment enables free and bidirectional mappings between sequences and structures by utilising the flexible RNA modelling paradigm that supports versatile input and output modalities, i.e., sequence and/or structure as input/output. We implement RNA design and zero-shot secondary structure prediction as case studies to evaluate the Seq2Str and Str2Seq mapping capacity of OmniGenome. Results on the EternaV2 benchmark show that OmniGenome solved 74% of puzzles, whereas existing FMs only solved up to 3% of the puzzles due to the oversight of sequence-structure alignment. We leverage four comprehensive in-silico genome modelling benchmarks to evaluate performance across a diverse set of genome downstream tasks, where the results show that OmniGenome achieves state-of-the-art performance on RNA and DNA benchmarks, even without any training on DNA genomes.

A key element in solving real-life data science problems is selecting the types of models to use. Tree ensemble models (such as XGBoost) are usually recommended for classification and regression problems with tabular data. However, several deep learning models for tabular data have recently been proposed, claiming to outperform XGBoost for some use cases. This paper explores whether these deep models should be a recommended option for tabular data by rigorously comparing the new deep models to XGBoost on various datasets. In addition to systematically comparing their performance, we consider the tuning and computation they require. Our study shows that XGBoost outperforms these deep models across the datasets, including the datasets used in the papers that proposed the deep models. We also demonstrate that XGBoost requires much less tuning. On the positive side, we show that an ensemble of deep models and XGBoost performs better on these datasets than XGBoost alone.

Tabular data is hard to acquire and is subject to missing values. This paper proposes a novel approach to generate and impute mixed-type (continuous and categorical) tabular data using score-based diffusion and conditional flow matching. Contrary to previous work that relies on neural networks as function approximators, we instead utilize XGBoost, a popular Gradient-Boosted Tree (GBT) method. In addition to being elegant, we empirically show on various datasets that our method i) generates highly realistic synthetic data when the training dataset is either clean or tainted by missing data and ii) generates diverse plausible data imputations. Our method often outperforms deep-learning generation methods and can trained in parallel using CPUs without the need for a GPU. To make it easily accessible, we release our code through a Python library on PyPI and an R package on CRAN.

While Chain-of-Thought (CoT) reasoning improves model performance, it incurs significant time costs due to the generation of discrete CoT tokens (DCoT). Continuous CoT (CCoT) offers a more efficient alternative, but existing CCoT methods are hampered by indirect fine-tuning, limited alignment, or inconsistent targets. To overcome these limitations, we propose SynAdapt, an innovative efficient reasoning framework. Specifically, SynAdapt generates the synthetic CCoT to serve as a precise and effective alignment target for LLMs. This synthetic CCoT explicitly guides the LLM to learn CCoT and derive accurate answers directly. Furthermore, relying solely on CCoT is insufficient for solving hard questions. To address this, SynAdapt integrates a difficulty classifier that leverages both question context and CCoT to identify hard questions. CCoT can effectively help identify hard questions after some brief reasoning. We then adaptively prompt the LLM to re-think these hard questions for improved performance. Extensive experimental results across various benchmarks from different difficulty levels strongly demonstrate the effectiveness of our method, achieving the best accuracy-efficiency trade-off.

The motif-scaffolding problem is a central task in computational protein design: Given the coordinates of atoms in a geometry chosen to confer a desired biochemical function (a motif), the task is to identify diverse protein structures (scaffolds) that include the motif and maintain its geometry. Significant recent progress on motif-scaffolding has been made due to computational evaluation with reliable protein structure prediction and fixed-backbone sequence design methods. However, significant variability in evaluation strategies across publications has hindered comparability of results, challenged reproducibility, and impeded robust progress. In response we introduce MotifBench, comprising (1) a precisely specified pipeline and evaluation metrics, (2) a collection of 30 benchmark problems, and (3) an implementation of this benchmark and leaderboard at github.com/blt2114/MotifBench. The MotifBench test cases are more difficult compared to earlier benchmarks, and include protein design problems for which solutions are known but on which, to the best of our knowledge, state-of-the-art methods fail to identify any solution.

Mathematical reasoning continues to be a critical challenge in large language model (LLM) development with significant interest. However, most of the cutting-edge progress in mathematical reasoning with LLMs has become closed-source due to lack of access to training data. This lack of data access limits researchers from understanding the impact of different choices for synthesizing and utilizing the data. With the goal of creating a high-quality finetuning (SFT) dataset for math reasoning, we conduct careful ablation experiments on data synthesis using the recently released Llama3.1 family of models. Our experiments show that: (a) solution format matters, with excessively verbose solutions proving detrimental to SFT performance, (b) data generated by a strong teacher outperforms on-policy data generated by a weak student model, (c) SFT is robust to low-quality solutions, allowing for imprecise data filtering, and (d) question diversity is crucial for achieving data scaling gains. Based on these insights, we create the OpenMathInstruct-2 dataset, which consists of 14M question-solution pairs (approx 600K unique questions), making it nearly eight times larger than the previous largest open-source math reasoning dataset. Finetuning the Llama-3.1-8B-Base using OpenMathInstruct-2 outperforms Llama3.1-8B-Instruct on MATH by an absolute 15.9\% (51.9\% rightarrow 67.8\%). Finally, to accelerate the open-source efforts, we release the code, the finetuned models, and the OpenMathInstruct-2 dataset under a commercially permissive license.

The field of bioinformatics has seen significant progress, making the cross-modal text-molecule retrieval task increasingly vital. This task focuses on accurately retrieving molecule structures based on textual descriptions, by effectively aligning textual descriptions and molecules to assist researchers in identifying suitable molecular candidates. However, many existing approaches overlook the details inherent in molecule sub-structures. In this work, we introduce the Optimal TRansport-based Multi-grained Alignments model (ORMA), a novel approach that facilitates multi-grained alignments between textual descriptions and molecules. Our model features a text encoder and a molecule encoder. The text encoder processes textual descriptions to generate both token-level and sentence-level representations, while molecules are modeled as hierarchical heterogeneous graphs, encompassing atom, motif, and molecule nodes to extract representations at these three levels. A key innovation in ORMA is the application of Optimal Transport (OT) to align tokens with motifs, creating multi-token representations that integrate multiple token alignments with their corresponding motifs. Additionally, we employ contrastive learning to refine cross-modal alignments at three distinct scales: token-atom, multitoken-motif, and sentence-molecule, ensuring that the similarities between correctly matched text-molecule pairs are maximized while those of unmatched pairs are minimized. To our knowledge, this is the first attempt to explore alignments at both the motif and multi-token levels. Experimental results on the ChEBI-20 and PCdes datasets demonstrate that ORMA significantly outperforms existing state-of-the-art (SOTA) models.

Graphs are able to model interconnected entities in many online services, supporting a wide range of applications on the Web. This raises an important question: How can we train a graph foundational model on multiple source domains and adapt to an unseen target domain? A major obstacle is that graphs from different domains often exhibit divergent characteristics. Some studies leverage large language models to align multiple domains based on textual descriptions associated with the graphs, limiting their applicability to text-attributed graphs. For text-free graphs, a few recent works attempt to align different feature distributions across domains, while generally neglecting structural differences. In this work, we propose a novel Structure Alignment framework for text-free Multi-domain Graph Pre-Training and cross-domain adaptation (SAMGPT). It is designed to learn multi-domain knowledge from graphs originating in multiple source domains, which can then be adapted to address applications in an unseen target domain. Specifically, we introduce a set of structure tokens to harmonize structure-based aggregation across source domains during the pre-training phase. Next, for cross-domain adaptation, we design dual prompts, namely, holistic prompts and specific prompts, which adapt unified multi-domain structural knowledge and fine-grained, domain-specific information, respectively, to a target domain. Finally, we conduct comprehensive experiments on seven public datasets to evaluate and analyze the effectiveness of SAMGPT.

As a fundamental task in computational chemistry, retrosynthesis prediction aims to identify a set of reactants to synthesize a target molecule. Existing template-free approaches only consider the graph structures of the target molecule, which often cannot generalize well to rare reaction types and large molecules. Here, we propose T-Rex, a text-assisted retrosynthesis prediction approach that exploits pre-trained text language models, such as ChatGPT, to assist the generation of reactants. T-Rex first exploits ChatGPT to generate a description for the target molecule and rank candidate reaction centers based both the description and the molecular graph. It then re-ranks these candidates by querying the descriptions for each reactants and examines which group of reactants can best synthesize the target molecule. We observed that T-Rex substantially outperformed graph-based state-of-the-art approaches on two datasets, indicating the effectiveness of considering text information. We further found that T-Rex outperformed the variant that only use ChatGPT-based description without the re-ranking step, demonstrate how our framework outperformed a straightforward integration of ChatGPT and graph information. Collectively, we show that text generated by pre-trained language models can substantially improve retrosynthesis prediction, opening up new avenues for exploiting ChatGPT to advance computational chemistry. And the codes can be found at https://github.com/lauyikfung/T-Rex.

We introduce XTREME-S, a new benchmark to evaluate universal cross-lingual speech representations in many languages. XTREME-S covers four task families: speech recognition, classification, speech-to-text translation and retrieval. Covering 102 languages from 10+ language families, 3 different domains and 4 task families, XTREME-S aims to simplify multilingual speech representation evaluation, as well as catalyze research in "universal" speech representation learning. This paper describes the new benchmark and establishes the first speech-only and speech-text baselines using XLS-R and mSLAM on all downstream tasks. We motivate the design choices and detail how to use the benchmark. Datasets and fine-tuning scripts are made easily accessible at https://hf.co/datasets/google/xtreme_s.

White matter bundle segmentation is crucial for studying brain structural connectivity, neurosurgical planning, and neurological disorders. White Matter Segmentation remains challenging due to structural similarity in streamlines, subject variability, symmetry in 2 hemispheres, etc. To address these challenges, we propose TractoGPT, a GPT-based architecture trained on streamline, cluster, and fusion data representations separately. TractoGPT is a fully-automatic method that generalizes across datasets and retains shape information of the white matter bundles. Experiments also show that TractoGPT outperforms state-of-the-art methods on average DICE, Overlap and Overreach scores. We use TractoInferno and 105HCP datasets and validate generalization across dataset.

Widely used learned metrics for machine translation evaluation, such as COMET and BLEURT, estimate the quality of a translation hypothesis by providing a single sentence-level score. As such, they offer little insight into translation errors (e.g., what are the errors and what is their severity). On the other hand, generative large language models (LLMs) are amplifying the adoption of more granular strategies to evaluation, attempting to detail and categorize translation errors. In this work, we introduce xCOMET, an open-source learned metric designed to bridge the gap between these approaches. xCOMET integrates both sentence-level evaluation and error span detection capabilities, exhibiting state-of-the-art performance across all types of evaluation (sentence-level, system-level, and error span detection). Moreover, it does so while highlighting and categorizing error spans, thus enriching the quality assessment. We also provide a robustness analysis with stress tests, and show that xCOMET is largely capable of identifying localized critical errors and hallucinations.

Generative pre-trained Transformer (GPT) has demonstrates its great success in natural language processing and related techniques have been adapted into molecular modeling. Considering that text is the most important record for scientific discovery, in this paper, we propose MolXPT, a unified language model of text and molecules pre-trained on SMILES (a sequence representation of molecules) wrapped by text. Briefly, we detect the molecule names in each sequence and replace them to the corresponding SMILES. In this way, the SMILES could leverage the information from surrounding text, and vice versa. The above wrapped sequences, text sequences from PubMed and SMILES sequences from PubChem are all fed into a language model for pre-training. Experimental results demonstrate that MolXPT outperforms strong baselines of molecular property prediction on MoleculeNet, performs comparably to the best model in text-molecule translation while using less than half of its parameters, and enables zero-shot molecular generation without finetuning.

Optimal transport aligns samples across distributions by minimizing the transportation cost between them, e.g., the geometric distances. Yet, it ignores coherence structure in the data such as clusters, does not handle outliers well, and cannot integrate new data points. To address these drawbacks, we propose InfoOT, an information-theoretic extension of optimal transport that maximizes the mutual information between domains while minimizing geometric distances. The resulting objective can still be formulated as a (generalized) optimal transport problem, and can be efficiently solved by projected gradient descent. This formulation yields a new projection method that is robust to outliers and generalizes to unseen samples. Empirically, InfoOT improves the quality of alignments across benchmarks in domain adaptation, cross-domain retrieval, and single-cell alignment.

Objective: To improve performance of medical entity normalization across many languages, especially when fewer language resources are available compared to English. Materials and Methods: We introduce xMEN, a modular system for cross-lingual medical entity normalization, which performs well in both low- and high-resource scenarios. When synonyms in the target language are scarce for a given terminology, we leverage English aliases via cross-lingual candidate generation. For candidate ranking, we incorporate a trainable cross-encoder model if annotations for the target task are available. We also evaluate cross-encoders trained in a weakly supervised manner based on machine-translated datasets from a high resource domain. Our system is publicly available as an extensible Python toolkit. Results: xMEN improves the state-of-the-art performance across a wide range of multilingual benchmark datasets. Weakly supervised cross-encoders are effective when no training data is available for the target task. Through the compatibility of xMEN with the BigBIO framework, it can be easily used with existing and prospective datasets. Discussion: Our experiments show the importance of balancing the output of general-purpose candidate generators with subsequent trainable re-rankers, which we achieve through a rank regularization term in the loss function of the cross-encoder. However, error analysis reveals that multi-word expressions and other complex entities are still challenging. Conclusion: xMEN exhibits strong performance for medical entity normalization in multiple languages, even when no labeled data and few terminology aliases for the target language are available. Its configuration system and evaluation modules enable reproducible benchmarks. Models and code are available online at the following URL: https://github.com/hpi-dhc/xmen

Long-Context Transformer Models (LCTMs) are vital for real-world applications but suffer high computational costs due to attention's quadratic complexity. Block-sparse attention mitigates this by focusing computation on critical regions, yet existing methods struggle with balancing accuracy and efficiency due to costly block importance measurements. In this paper, we introduce XAttention, a plug-and-play framework that dramatically accelerates long-context inference in Transformers models using sparse attention. XAttention's key innovation is the insight that the sum of antidiagonal values (i.e., from the lower-left to upper-right) in the attention matrix provides a powerful proxy for block importance. This allows for precise identification and pruning of non-essential blocks, resulting in high sparsity and dramatically accelerated inference. Across comprehensive evaluations on demanding long-context benchmarks-including RULER and LongBench for language, VideoMME for video understanding, and VBench for video generation. XAttention achieves accuracy comparable to full attention while delivering substantial computational gains. We demonstrate up to 13.5x acceleration in attention computation. These results underscore XAttention's ability to unlock the practical potential of block sparse attention, paving the way for scalable and efficient deployment of LCTMs in real-world applications. Code is available at https://github.com/mit-han-lab/x-attention.

Large language models (LLMs) with Chain-of-thought (CoT) have recently emerged as a powerful technique for eliciting reasoning to improve various downstream tasks. As most research mainly focuses on English, with few explorations in a multilingual context, the question of how reliable this reasoning capability is in different languages is still open. To address it directly, we study multilingual reasoning consistency across multiple languages, using popular open-source LLMs. First, we compile the first large-scale multilingual math reasoning dataset, mCoT-MATH, covering eleven diverse languages. Then, we introduce multilingual CoT instruction tuning to boost reasoning capability across languages, thereby improving model consistency. While existing LLMs show substantial variation across the languages we consider, and especially low performance for lesser resourced languages, our 7B parameter model mCoT achieves impressive consistency across languages, and superior or comparable performance to close- and open-source models even of much larger sizes.

Platforms such as GitHub and GitLab introduce Issue Report Templates (IRTs) to enable more effective issue management and better alignment with developer expectations. However, these templates are not widely adopted in most repositories, and there is currently no tool available to aid developers in generating them. In this work, we introduce GIRT-Model, an assistant language model that automatically generates IRTs based on the developer's instructions regarding the structure and necessary fields. We create GIRT-Instruct, a dataset comprising pairs of instructions and IRTs, with the IRTs sourced from GitHub repositories. We use GIRT-Instruct to instruction-tune a T5-base model to create the GIRT-Model. In our experiments, GIRT-Model outperforms general language models (T5 and Flan-T5 with different parameter sizes) in IRT generation by achieving significantly higher scores in ROUGE, BLEU, METEOR, and human evaluation. Additionally, we analyze the effectiveness of GIRT-Model in a user study in which participants wrote short IRTs with GIRT-Model. Our results show that the participants find GIRT-Model useful in the automated generation of templates. We hope that through the use of GIRT-Model, we can encourage more developers to adopt IRTs in their repositories. We publicly release our code, dataset, and model at https://github.com/ISE-Research/girt-model.

Structural topology optimization (TO) is central to engineering design but remains computationally intensive due to complex physics and hard constraints. Existing deep-learning methods are limited to fixed square grids, a few hand-coded boundary conditions, and post-hoc optimization, preventing general deployment. We introduce Optimize Any Topology (OAT), a foundation-model framework that directly predicts minimum-compliance layouts for arbitrary aspect ratios, resolutions, volume fractions, loads, and fixtures. OAT combines a resolution- and shape-agnostic autoencoder with an implicit neural-field decoder and a conditional latent-diffusion model trained on OpenTO, a new corpus of 2.2 million optimized structures covering 2 million unique boundary-condition configurations. On four public benchmarks and two challenging unseen tests, OAT lowers mean compliance up to 90% relative to the best prior models and delivers sub-1 second inference on a single GPU across resolutions from 64 x 64 to 256 x 256 and aspect ratios as high as 10:1. These results establish OAT as a general, fast, and resolution-free framework for physics-aware topology optimization and provide a large-scale dataset to spur further research in generative modeling for inverse design. Code & data can be found at https://github.com/ahnobari/OptimizeAnyTopology.

Chest X-rays (CXRs) are the most frequently performed imaging test in clinical practice. Recent advances in the development of vision-language foundation models (FMs) give rise to the possibility of performing automated CXR interpretation, which can assist physicians with clinical decision-making and improve patient outcomes. However, developing FMs that can accurately interpret CXRs is challenging due to the (1) limited availability of large-scale vision-language datasets in the medical image domain, (2) lack of vision and language encoders that can capture the complexities of medical data, and (3) absence of evaluation frameworks for benchmarking the abilities of FMs on CXR interpretation. In this work, we address these challenges by first introducing CheXinstruct - a large-scale instruction-tuning dataset curated from 28 publicly-available datasets. We then present CheXagent - an instruction-tuned FM capable of analyzing and summarizing CXRs. To build CheXagent, we design a clinical large language model (LLM) for parsing radiology reports, a vision encoder for representing CXR images, and a network to bridge the vision and language modalities. Finally, we introduce CheXbench - a novel benchmark designed to systematically evaluate FMs across 8 clinically-relevant CXR interpretation tasks. Extensive quantitative evaluations and qualitative reviews with five expert radiologists demonstrate that CheXagent outperforms previously-developed general- and medical-domain FMs on CheXbench tasks. Furthermore, in an effort to improve model transparency, we perform a fairness evaluation across factors of sex, race and age to highlight potential performance disparities. Our project is at https://stanford-aimi.github.io/chexagent.html.

Generalizing deep learning models to unknown target domain distribution with low latency has motivated research into test-time training/adaptation (TTT/TTA). Existing approaches often focus on improving test-time training performance under well-curated target domain data. As figured out in this work, many state-of-the-art methods fail to maintain the performance when the target domain is contaminated with strong out-of-distribution (OOD) data, a.k.a. open-world test-time training (OWTTT). The failure is mainly due to the inability to distinguish strong OOD samples from regular weak OOD samples. To improve the robustness of OWTTT we first develop an adaptive strong OOD pruning which improves the efficacy of the self-training TTT method. We further propose a way to dynamically expand the prototypes to represent strong OOD samples for an improved weak/strong OOD data separation. Finally, we regularize self-training with distribution alignment and the combination yields the state-of-the-art performance on 5 OWTTT benchmarks. The code is available at https://github.com/Yushu-Li/OWTTT.

Cancer is the second leading cause of death, with chemotherapy as one of the primary forms of treatment. As a result, researchers are turning to drug combination therapy to decrease drug resistance and increase efficacy. Current methods of drug combination screening, such as in vivo and in vitro, are inefficient due to stark time and monetary costs. In silico methods have become increasingly important for screening drugs, but current methods are inaccurate and generalize poorly to unseen anticancer drugs. In this paper, I employ a geometric deep-learning model utilizing a graph attention network that is equivariant to 3D rotations, translations, and reflections with structural motifs. Additionally, the gene expression of cancer cell lines is utilized to classify synergistic drug combinations specific to each cell line. I compared the proposed geometric deep learning framework to current state-of-the-art (SOTA) methods, and the proposed model architecture achieved greater performance on all 12 benchmark tasks performed on the DrugComb dataset. Specifically, the proposed framework outperformed other SOTA methods by an accuracy difference greater than 28%. Based on these results, I believe that the equivariant graph attention network's capability of learning geometric data accounts for the large performance improvements. The model's ability to generalize to foreign drugs is thought to be due to the structural motifs providing a better representation of the molecule. Overall, I believe that the proposed equivariant geometric deep learning framework serves as an effective tool for virtually screening anticancer drug combinations for further validation in a wet lab environment. The code for this work is made available online at: https://github.com/WeToTheMoon/EGAT_DrugSynergy.

Electrocardiograms (ECGs) are inexpensive, widely used, and well-suited to deep learning. Recently, interest has grown in developing foundation models for ECGs - models that generalise across diverse downstream tasks. However, consistent evaluation has been lacking: prior work often uses narrow task selections and inconsistent datasets, hindering fair comparison. Here, we introduce BenchECG, a standardised benchmark comprising a comprehensive suite of publicly available ECG datasets and versatile tasks. We also propose xECG, an xLSTM-based recurrent model trained with SimDINOv2 self-supervised learning, which achieves the best BenchECG score compared to publicly available state-of-the-art models. In particular, xECG is the only publicly available model to perform strongly on all datasets and tasks. By standardising evaluation, BenchECG enables rigorous comparison and aims to accelerate progress in ECG representation learning. xECG achieves superior performance over earlier approaches, defining a new baseline for future ECG foundation models.

We introduce an Extended Textual Conditioning space in text-to-image models, referred to as P+. This space consists of multiple textual conditions, derived from per-layer prompts, each corresponding to a layer of the denoising U-net of the diffusion model. We show that the extended space provides greater disentangling and control over image synthesis. We further introduce Extended Textual Inversion (XTI), where the images are inverted into P+, and represented by per-layer tokens. We show that XTI is more expressive and precise, and converges faster than the original Textual Inversion (TI) space. The extended inversion method does not involve any noticeable trade-off between reconstruction and editability and induces more regular inversions. We conduct a series of extensive experiments to analyze and understand the properties of the new space, and to showcase the effectiveness of our method for personalizing text-to-image models. Furthermore, we utilize the unique properties of this space to achieve previously unattainable results in object-style mixing using text-to-image models. Project page: https://prompt-plus.github.io

In this paper, we address the challenging task of multimodal mathematical reasoning by incorporating the ability of "slow thinking" into multimodal large language models (MLLMs). Our core idea is that different levels of reasoning abilities can be combined dynamically to tackle questions with different complexity. To this end, we propose a paradigm of Self-structured Chain of Thought (SCoT), which is composed of minimal semantic atomic steps. Different from existing methods that rely on structured templates or free-form paradigms, our method can not only generate cognitive CoT structures for various complex tasks but also mitigates the phenomenon of overthinking. To introduce structured reasoning capabilities into visual understanding models, we further design a novel AtomThink framework with four key modules, including (i) a data engine to generate high-quality multimodal reasoning paths; (ii) a supervised fine-tuning process with serialized inference data; (iii) a policy-guided multi-turn inference method; and (iv) an atomic capability metric to evaluate the single step utilization rate. We conduct extensive experiments to show that the proposed AtomThink significantly improves the performance of baseline MLLMs, achieving more than 10\% average accuracy gains on MathVista and MathVerse. Compared to state-of-the-art structured CoT approaches, our method not only achieves higher accuracy but also improves data utilization by 5 times and boosts inference efficiency by 85.3\%. Our code is now public available in https://github.com/Quinn777/AtomThink.

Continual Test-Time Adaptation (CTTA) aims to adapt a pretrained model to ever-changing environments during the test time under continuous domain shifts. Most existing CTTA approaches are based on the Mean Teacher (MT) structure, which contains a student and a teacher model, where the student is updated using the pseudo-labels from the teacher model, and the teacher is then updated by exponential moving average strategy. However, these methods update the MT model indiscriminately on all parameters of the model. That is, some critical parameters involving sharing knowledge across different domains may be erased, intensifying error accumulation and catastrophic forgetting. In this paper, we introduce Parameter-Selective Mean Teacher (PSMT) method, which is capable of effectively updating the critical parameters within the MT network under domain shifts. First, we introduce a selective distillation mechanism in the student model, which utilizes past knowledge to regularize novel knowledge, thereby mitigating the impact of error accumulation. Second, to avoid catastrophic forgetting, in the teacher model, we create a mask through Fisher information to selectively update parameters via exponential moving average, with preservation measures applied to crucial parameters. Extensive experimental results verify that PSMT outperforms state-of-the-art methods across multiple benchmark datasets. Our code is available at https://github.com/JiaxuTian/PSMT.

Text-driven motion generation has attracted increasing attention due to its broad applications in virtual reality, animation, and robotics. While existing methods typically model human and animal motion separately, a joint cross-species approach offers key advantages, such as a unified representation and improved generalization. However, morphological differences across species remain a key challenge, often compromising motion plausibility. To address this, we propose X-MoGen, the first unified framework for cross-species text-driven motion generation covering both humans and animals. X-MoGen adopts a two-stage architecture. First, a conditional graph variational autoencoder learns canonical T-pose priors, while an autoencoder encodes motion into a shared latent space regularized by morphological loss. In the second stage, we perform masked motion modeling to generate motion embeddings conditioned on textual descriptions. During training, a morphological consistency module is employed to promote skeletal plausibility across species. To support unified modeling, we construct UniMo4D, a large-scale dataset of 115 species and 119k motion sequences, which integrates human and animal motions under a shared skeletal topology for joint training. Extensive experiments on UniMo4D demonstrate that X-MoGen outperforms state-of-the-art methods on both seen and unseen species.

We propose X-Fusion, a framework that extends pretrained Large Language Models (LLMs) for multimodal tasks while preserving their language capabilities. X-Fusion employs a dual-tower design with modality-specific weights, keeping the LLM's parameters frozen while integrating vision-specific information for both understanding and generation. Our experiments demonstrate that X-Fusion consistently outperforms alternative architectures on both image-to-text and text-to-image tasks. We find that incorporating understanding-focused data improves generation quality, reducing image data noise enhances overall performance, and feature alignment accelerates convergence for smaller models but has minimal impact on larger ones. Our findings provide valuable insights into building efficient unified multimodal models.

Proteins are essential biological macromolecules that execute life functions. Local motifs within protein structures, such as active sites, are the most critical components for linking structure to function and are key to understanding protein evolution and enabling protein engineering. Existing computational methods struggle to identify and compare these local structures, which leaves a significant gap in understanding protein structures and harnessing their functions. This study presents PLASMA, the first deep learning framework for efficient and interpretable residue-level protein substructure alignment. We reformulate the problem as a regularized optimal transport task and leverage differentiable Sinkhorn iterations. For a pair of input protein structures, PLASMA outputs a clear alignment matrix with an interpretable overall similarity score. Through extensive quantitative evaluations and three biological case studies, we demonstrate that PLASMA achieves accurate, lightweight, and interpretable residue-level alignment. Additionally, we introduce PLASMA-PF, a training-free variant that provides a practical alternative when training data are unavailable. Our method addresses a critical gap in protein structure analysis tools and offers new opportunities for functional annotation, evolutionary studies, and structure-based drug design. Reproducibility is ensured via our official implementation at https://github.com/ZW471/PLASMA-Protein-Local-Alignment.git.

We introduce X-VILA, an omni-modality model designed to extend the capabilities of large language models (LLMs) by incorporating image, video, and audio modalities. By aligning modality-specific encoders with LLM inputs and diffusion decoders with LLM outputs, X-VILA achieves cross-modality understanding, reasoning, and generation. To facilitate this cross-modality alignment, we curate an effective interleaved any-to-any modality instruction-following dataset. Furthermore, we identify a significant problem with the current cross-modality alignment method, which results in visual information loss. To address the issue, we propose a visual alignment mechanism with a visual embedding highway module. We then introduce a resource-efficient recipe for training X-VILA, that exhibits proficiency in any-to-any modality conversation, surpassing previous approaches by large margins. X-VILA also showcases emergent properties across modalities even in the absence of similar training data. The project will be made open-source.

This paper describes the FBK's participation in the Simultaneous Translation Evaluation Campaign at IWSLT 2024. For this year's submission in the speech-to-text translation (ST) sub-track, we propose SimulSeamless, which is realized by combining AlignAtt and SeamlessM4T in its medium configuration. The SeamlessM4T model is used "off-the-shelf" and its simultaneous inference is enabled through the adoption of AlignAtt, a SimulST policy based on cross-attention that can be applied without any retraining or adaptation of the underlying model for the simultaneous task. We participated in all the Shared Task languages (English->{German, Japanese, Chinese}, and Czech->English), achieving acceptable or even better results compared to last year's submissions. SimulSeamless, covering more than 143 source languages and 200 target languages, is released at: https://github.com/hlt-mt/FBK-fairseq/.

Although LLM inference has emerged as a critical workload for many downstream applications, efficiently inferring LLMs is challenging due to the substantial memory footprint and bandwidth requirements. In parallel, compute capabilities have steadily outpaced both memory capacity and bandwidth over the last few decades, a trend that remains evident in modern GPU hardware and exacerbates the challenge of LLM inference. As such, new algorithms are emerging that trade increased computation for reduced memory operations. To that end, we present XQuant, which takes advantage of this trend, enabling an order-of-magnitude reduction in memory consumption through low-bit quantization with substantial accuracy benefits relative to state-of-the-art KV cache quantization methods. We accomplish this by quantizing and caching the layer input activations X, instead of using standard KV caching, and then rematerializing the Keys and Values on-the-fly during inference. This results in an immediate 2times memory savings compared to KV caching. By applying XQuant, we achieve up to sim 7.7times memory savings with <0.1 perplexity degradation compared to the FP16 baseline. Furthermore, our approach leverages the fact that X values are similar across layers. Building on this observation, we introduce XQuant-CL, which exploits the cross-layer similarity in the X embeddings for extreme compression. Across different models, XQuant-CL attains up to 10times memory savings relative to the FP16 baseline with only 0.01 perplexity degradation, and 12.5times memory savings with only 0.1 perplexity degradation. XQuant exploits the rapidly increasing compute capabilities of hardware platforms to eliminate the memory bottleneck, while surpassing state-of-the-art KV cache quantization methods and achieving near-FP16 accuracy across a wide range of models.

Recently, visually-situated text parsing (VsTP) has experienced notable advancements, driven by the increasing demand for automated document understanding and the emergence of Generative Large Language Models (LLMs) capable of processing document-based questions. Various methods have been proposed to address the challenging problem of VsTP. However, due to the diversified targets and heterogeneous schemas, previous works usually design task-specific architectures and objectives for individual tasks, which inadvertently leads to modal isolation and complex workflow. In this paper, we propose a unified paradigm for parsing visually-situated text across diverse scenarios. Specifically, we devise a universal model, called OmniParser, which can simultaneously handle three typical visually-situated text parsing tasks: text spotting, key information extraction, and table recognition. In OmniParser, all tasks share the unified encoder-decoder architecture, the unified objective: point-conditioned text generation, and the unified input & output representation: prompt & structured sequences. Extensive experiments demonstrate that the proposed OmniParser achieves state-of-the-art (SOTA) or highly competitive performances on 7 datasets for the three visually-situated text parsing tasks, despite its unified, concise design. The code is available at https://github.com/AlibabaResearch/AdvancedLiterateMachinery.

In multi-task learning, the conventional approach involves training a model on multiple tasks simultaneously. However, the training signals from different tasks can interfere with one another, potentially leading to negative transfer. To mitigate this, we investigate if modular language models can facilitate positive transfer and systematic generalization. Specifically, we propose a novel modular language model (TensorPoly), that balances parameter efficiency with nuanced routing methods. For modules, we reparameterize Low-Rank Adaptation (LoRA) by employing an entangled tensor through the use of tensor product operations and name the resulting approach TLoRA. For routing function, we tailor two innovative routing functions according to the granularity: TensorPoly-I which directs to each rank within the entangled tensor while TensorPoly-II offers a finer-grained routing approach targeting each order of the entangled tensor. The experimental results from the multi-task T0-benchmark demonstrate that: 1) all modular LMs surpass the corresponding dense approaches, highlighting the potential of modular language models to mitigate negative inference in multi-task learning and deliver superior outcomes. 2) TensorPoly-I achieves higher parameter efficiency in adaptation and outperforms other modular LMs, which shows the potential of our approach in multi-task transfer learning.

Structure-Based Drug Design (SBDD) is crucial for identifying bioactive molecules. Recent deep generative models are faced with challenges in geometric structure modeling. A major bottleneck lies in the twisted probability path of multi-modalities -- continuous 3D positions and discrete 2D topologies -- which jointly determine molecular geometries. By establishing the fact that noise schedules decide the Variational Lower Bound (VLB) for the twisted probability path, we propose VLB-Optimal Scheduling (VOS) strategy in this under-explored area, which optimizes VLB as a path integral for SBDD. Our model effectively enhances molecular geometries and interaction modeling, achieving state-of-the-art PoseBusters passing rate of 95.9% on CrossDock, more than 10% improvement upon strong baselines, while maintaining high affinities and robust intramolecular validity evaluated on held-out test set. Code is available at https://github.com/AlgoMole/MolCRAFT.

Current AI-assisted protein design mainly utilizes protein sequential and structural information. Meanwhile, there exists tremendous knowledge curated by humans in the text format describing proteins' high-level properties. Yet, whether the incorporation of such text data can help protein design tasks has not been explored. To bridge this gap, we propose ProteinDT, a multi-modal framework that leverages textual descriptions for protein design. ProteinDT consists of three subsequent steps: ProteinCLAP that aligns the representation of two modalities, a facilitator that generates the protein representation from the text modality, and a decoder that generates the protein sequences from the representation. To train ProteinDT, we construct a large dataset, SwissProtCLAP, with 441K text and protein pairs. We empirically verify the effectiveness of ProteinDT from three aspects: (1) consistently superior performance on four out of six protein property prediction benchmarks; (2) over 90% accuracy for text-guided protein generation; and (3) promising results for zero-shot text-guided protein editing.

Visually-situated text parsing (VsTP) has recently seen notable advancements, driven by the growing demand for automated document understanding and the emergence of large language models capable of processing document-based questions. While various methods have been proposed to tackle the complexities of VsTP, existing solutions often rely on task-specific architectures and objectives for individual tasks. This leads to modal isolation and complex workflows due to the diversified targets and heterogeneous schemas. In this paper, we introduce OmniParser V2, a universal model that unifies VsTP typical tasks, including text spotting, key information extraction, table recognition, and layout analysis, into a unified framework. Central to our approach is the proposed Structured-Points-of-Thought (SPOT) prompting schemas, which improves model performance across diverse scenarios by leveraging a unified encoder-decoder architecture, objective, and input\&output representation. SPOT eliminates the need for task-specific architectures and loss functions, significantly simplifying the processing pipeline. Our extensive evaluations across four tasks on eight different datasets show that OmniParser V2 achieves state-of-the-art or competitive results in VsTP. Additionally, we explore the integration of SPOT within a multimodal large language model structure, further enhancing text localization and recognition capabilities, thereby confirming the generality of SPOT prompting technique. The code is available at https://github.com/AlibabaResearch/AdvancedLiterateMachinery{AdvancedLiterateMachinery}.

Scaling up model and data size has been quite successful for the evolution of LLMs. However, the scaling law for the diffusion based text-to-image (T2I) models is not fully explored. It is also unclear how to efficiently scale the model for better performance at reduced cost. The different training settings and expensive training cost make a fair model comparison extremely difficult. In this work, we empirically study the scaling properties of diffusion based T2I models by performing extensive and rigours ablations on scaling both denoising backbones and training set, including training scaled UNet and Transformer variants ranging from 0.4B to 4B parameters on datasets upto 600M images. For model scaling, we find the location and amount of cross attention distinguishes the performance of existing UNet designs. And increasing the transformer blocks is more parameter-efficient for improving text-image alignment than increasing channel numbers. We then identify an efficient UNet variant, which is 45% smaller and 28% faster than SDXL's UNet. On the data scaling side, we show the quality and diversity of the training set matters more than simply dataset size. Increasing caption density and diversity improves text-image alignment performance and the learning efficiency. Finally, we provide scaling functions to predict the text-image alignment performance as functions of the scale of model size, compute and dataset size.

Understanding the relationships between protein sequence, structure and function is a long-standing biological challenge with manifold implications from drug design to our understanding of evolution. Recently, protein language models have emerged as the preferred method for this challenge, thanks to their ability to harness large sequence databases. Yet, their reliance on expansive sequence data and parameter sets limits their flexibility and practicality in real-world scenarios. Concurrently, the recent surge in computationally predicted protein structures unlocks new opportunities in protein representation learning. While promising, the computational burden carried by such complex data still hinders widely-adopted practical applications. To address these limitations, we introduce a novel framework that enhances protein language models by integrating protein structural data. Drawing from recent advances in graph transformers, our approach refines the self-attention mechanisms of pretrained language transformers by integrating structural information with structure extractor modules. This refined model, termed Protein Structure Transformer (PST), is further pretrained on a small protein structure database, using the same masked language modeling objective as traditional protein language models. Empirical evaluations of PST demonstrate its superior parameter efficiency relative to protein language models, despite being pretrained on a dataset comprising only 542K structures. Notably, PST consistently outperforms the state-of-the-art foundation model for protein sequences, ESM-2, setting a new benchmark in protein function prediction. Our findings underscore the potential of integrating structural information into protein language models, paving the way for more effective and efficient protein modeling Code and pretrained models are available at https://github.com/BorgwardtLab/PST.

As new products are emerging daily, recommendation systems are required to quickly adapt to possible new domains without needing extensive retraining. This work presents ``X-Cross'' -- a novel cross-domain sequential-recommendation model that recommends products in new domains by integrating several domain-specific language models; each model is fine-tuned with low-rank adapters (LoRA). Given a recommendation prompt, operating layer by layer, X-Cross dynamically refines the representation of each source language model by integrating knowledge from all other models. These refined representations are propagated from one layer to the next, leveraging the activations from each domain adapter to ensure domain-specific nuances are preserved while enabling adaptability across domains. Using Amazon datasets for sequential recommendation, X-Cross achieves performance comparable to a model that is fine-tuned with LoRA, while using only 25% of the additional parameters. In cross-domain tasks, such as adapting from Toys domain to Tools, Electronics or Sports, X-Cross demonstrates robust performance, while requiring about 50%-75% less fine-tuning data than LoRA to make fine-tuning effective. Furthermore, X-Cross achieves significant improvement in accuracy over alternative cross-domain baselines. Overall, X-Cross enables scalable and adaptive cross-domain recommendations, reducing computational overhead and providing an efficient solution for data-constrained environments.

Density Functional Theory (DFT) is the most widely used electronic structure method for predicting the properties of molecules and materials. Although DFT is, in principle, an exact reformulation of the Schr\"odinger equation, practical applications rely on approximations to the unknown exchange-correlation (XC) functional. Most existing XC functionals are constructed using a limited set of increasingly complex, hand-crafted features that improve accuracy at the expense of computational efficiency. Yet, no current approximation achieves the accuracy and generality for predictive modeling of laboratory experiments at chemical accuracy -- typically defined as errors below 1 kcal/mol. In this work, we present Skala, a modern deep learning-based XC functional that bypasses expensive hand-designed features by learning representations directly from data. Skala achieves chemical accuracy for atomization energies of small molecules while retaining the computational efficiency typical of semi-local DFT. This performance is enabled by training on an unprecedented volume of high-accuracy reference data generated using computationally intensive wavefunction-based methods. Notably, Skala systematically improves with additional training data covering diverse chemistry. By incorporating a modest amount of additional high-accuracy data tailored to chemistry beyond atomization energies, Skala achieves accuracy competitive with the best-performing hybrid functionals across general main group chemistry, at the cost of semi-local DFT. As the training dataset continues to expand, Skala is poised to further enhance the predictive power of first-principles simulations.

Multi-task learning has the potential to improve generalization by maximizing positive transfer between tasks while reducing task interference. Fully achieving this potential is hindered by manually designed architectures that remain static throughout training. On the contrary, learning in the brain occurs through structural changes that are in tandem with changes in synaptic strength. Thus, we propose Multi-Task Structural Learning (MTSL) that simultaneously learns the multi-task architecture and its parameters. MTSL begins with an identical single-task network for each task and alternates between a task-learning phase and a structural-learning phase. In the task learning phase, each network specializes in the corresponding task. In each of the structural learning phases, starting from the earliest layer, locally similar task layers first transfer their knowledge to a newly created group layer before being removed. MTSL then uses the group layer in place of the corresponding removed task layers and moves on to the next layers. Our empirical results show that MTSL achieves competitive generalization with various baselines and improves robustness to out-of-distribution data.

Recent parameter-efficient finetuning (PEFT) techniques aim to improve over the considerable cost of fully finetuning large pretrained language models (PLM). As different PEFT techniques proliferate, it is becoming difficult to compare them, in particular in terms of (i) the structure and functionality they add to the PLM, (ii) the different types and degrees of efficiency improvements achieved, (iii) performance at different downstream tasks, and (iv) how differences in structure and functionality relate to efficiency and task performance. To facilitate such comparisons, this paper presents a reference architecture which standardises aspects shared by different PEFT techniques, while isolating differences to specific locations and interactions with the standard components. Through this process of standardising and isolating differences, a modular view of PEFT techniques emerges, supporting not only direct comparison of different techniques and their efficiency and task performance, but also systematic exploration of reusability and composability of the different types of finetuned modules. We demonstrate how the reference architecture can be applied to understand properties and relative advantages of PEFT techniques, hence to inform selection of techniques for specific tasks, and design choices for new PEFT techniques.

Large language models (LLMs) are increasingly employed for complex multi-step planning tasks, where the tool retrieval (TR) step is crucial for achieving successful outcomes. Two prevalent approaches for TR are single-step retrieval, which utilizes the complete query, and sequential retrieval using task decomposition (TD), where a full query is segmented into discrete atomic subtasks. While single-step retrieval lacks the flexibility to handle "inter-tool dependency," the TD approach necessitates maintaining "subtask-tool atomicity alignment," as the toolbox can evolve dynamically. To address these limitations, we introduce the Progressive Tool retrieval to Improve Planning (ProTIP) framework. ProTIP is a lightweight, contrastive learning-based framework that implicitly performs TD without the explicit requirement of subtask labels, while simultaneously maintaining subtask-tool atomicity. On the ToolBench dataset, ProTIP outperforms the ChatGPT task decomposition-based approach by a remarkable margin, achieving a 24% improvement in Recall@K=10 for TR and a 41% enhancement in tool accuracy for plan generation.

Large language models (LLMs) typically employ sampling or beam search, accompanied by prompts such as Chain-of-Thought (CoT), to boost reasoning and decoding ability. Recent work like Tree-of-Thought (ToT) and Reasoning via Planning (RAP) aim to augment the reasoning capabilities of LLMs by utilizing tree-search algorithms to guide multi-step reasoning. These methods mainly focus on LLMs' reasoning ability during inference and heavily rely on human-designed prompts to activate LLM as a value function, which lacks general applicability and scalability. To address these limitations, we present an AlphaZero-like tree-search framework for LLMs (termed TS-LLM), systematically illustrating how tree-search with a learned value function can guide LLMs' decoding ability. TS-LLM distinguishes itself in two key ways: (1) Leveraging a learned value function, our approach can be generally applied to different tasks beyond reasoning (such as RLHF alignment), and LLMs of any size, without prompting advanced, large-scale models. (2) It can guide LLM's decoding during both inference and training. Empirical evaluations across reasoning, planning, and RLHF alignment tasks validate the effectiveness of TS-LLM, even on trees with a depth of 64.

Multilingual question answering tasks typically assume answers exist in the same language as the question. Yet in practice, many languages face both information scarcity -- where languages have few reference articles -- and information asymmetry -- where questions reference concepts from other cultures. This work extends open-retrieval question answering to a cross-lingual setting enabling questions from one language to be answered via answer content from another language. We construct a large-scale dataset built on questions from TyDi QA lacking same-language answers. Our task formulation, called Cross-lingual Open Retrieval Question Answering (XOR QA), includes 40k information-seeking questions from across 7 diverse non-English languages. Based on this dataset, we introduce three new tasks that involve cross-lingual document retrieval using multi-lingual and English resources. We establish baselines with state-of-the-art machine translation systems and cross-lingual pretrained models. Experimental results suggest that XOR QA is a challenging task that will facilitate the development of novel techniques for multilingual question answering. Our data and code are available at https://nlp.cs.washington.edu/xorqa.

Transition state (TS) structures define the critical geometries and energy barriers underlying chemical reactivity, yet their fleeting nature renders them experimentally elusive and drives the reliance on costly, high-throughput density functional theory (DFT) calculations. Here, we introduce TS-GEN, a conditional flow-matching generative model that maps samples from a simple Gaussian prior directly to transition-state saddle-point geometries in a single, deterministic pass. By embedding both reactant and product conformations as conditioning information, TS-GEN learns to transport latent noise to true TS structures via an optimal-transport path, effectively replacing the iterative optimization common in nudged-elastic band or string-method algorithms. TS-GEN delivers unprecedented accuracy, achieving a root-mean-square deviation of 0.004 mathring{A} (vs. 0.103 mathring{A} for prior state-of-the-art) and a mean barrier-height error of 1.019 {rm kcal/mol} (vs. 2.864 {rm kcal/mol}), while requiring only 0.06 {rm s} GPU time per inference. Over 87% of generated TSs meet chemical-accuracy criteria (<1.58 {rm kcal/mol} error), substantially outpacing existing methods. TS-GEN also exhibits strong transferability to out-of-distribution reactions from a larger database. By uniting sub-angstrom precision, sub-second speed, and broad applicability, TS-GEN will be highly useful for high-throughput exploration of complex reaction networks, paving the way to the exploration of novel chemical reaction mechanisms.

Vector Symbolic Architectures (VSAs) give a way to represent a complex object as a single fixed-length vector, so that similar objects have similar vector representations. These vector representations then become easy to use for machine learning or nearest-neighbor search. We review a previously proposed VSA method, MBAT (Matrix Binding of Additive Terms), which uses multiplication by random matrices for binding related terms. However, multiplying by such matrices introduces instabilities which can harm performance. Making the random matrices be orthogonal matrices provably fixes this problem. With respect to larger scale applications, we see how to apply MBAT vector representations for any data expressed in JSON. JSON is used in numerous programming languages to express complex data, but its native format appears highly unsuited for machine learning. Expressing JSON as a fixed-length vector makes it readily usable for machine learning and nearest-neighbor search. Creating such JSON vectors also shows that a VSA needs to employ binding operations that are non-commutative. VSAs are now ready to try with full-scale practical applications, including healthcare, pharmaceuticals, and genomics. Keywords: MBAT (Matrix Binding of Additive Terms), VSA (Vector Symbolic Architecture), HDC (Hyperdimensional Computing), Distributed Representations, Binding, Orthogonal Matrices, Recurrent Connections, Machine Learning, Search, JSON, VSA Applications

Novel machine learning methods for tabular data generation are often developed on small datasets which do not match the scale required for scientific applications. We investigate a recent proposal to use XGBoost as the function approximator in diffusion and flow-matching models on tabular data, which proved to be extremely memory intensive, even on tiny datasets. In this work, we conduct a critical analysis of the existing implementation from an engineering perspective, and show that these limitations are not fundamental to the method; with better implementation it can be scaled to datasets 370x larger than previously used. Our efficient implementation also unlocks scaling models to much larger sizes which we show directly leads to improved performance on benchmark tasks. We also propose algorithmic improvements that can further benefit resource usage and model performance, including multi-output trees which are well-suited to generative modeling. Finally, we present results on large-scale scientific datasets derived from experimental particle physics as part of the Fast Calorimeter Simulation Challenge. Code is available at https://github.com/layer6ai-labs/calo-forest.

Zero-shot models like CLIP are often fine-tuned on a target dataset to improve its accuracy further, but this can compromise out-of-distribution (OOD) robustness. Robust Fine-Tuning (RFT )~wortsman2021robust, which interpolates between the zero-shot and fine-tuned models, has been proposed to address this issue. However, understanding when RFT actually improves OOD error remains limited. In this work, we empirically investigate the robustness of RFT in CLIP models, with a focus on the sharpness of the CLIP model during interpolation. First, we demonstrate that while sharpness may not serve as a reliable indicator for predicting the generalization of modern architectures like CLIP on OOD data, this challenges the conventional belief in the generalization benefits of flat minima in foundation models. However, by examining the role of the straggler layer phenomenon, we show that, unlike overall sharpness, the layer-wise sharpness of straggler layers can reliably capture the generalization performance of interpolated CLIP models on OOD data. Our extensive experiments reveal that layer-wise sharpness correlates with generalization in OOD accuracy for RFT. Furthermore, we demonstrate that by inducing sparsity in the straggler layers, we can mitigate the failure mode phenomenon in RFT. To the best of our knowledge, this is the first work to study the role of sharpness in the success of interpolation in the weight space of CLIP foundation models. Our code is available at https://github.com/alirezaabdollahpour/CLIP_Mode_Connectivity.

In this paper, we present a new MTL framework that searches for structures optimized for multiple tasks with diverse graph topologies and shares features among tasks. We design a restricted DAG-based central network with read-in/read-out layers to build topologically diverse task-adaptive structures while limiting search space and time. We search for a single optimized network that serves as multiple task adaptive sub-networks using our three-stage training process. To make the network compact and discretized, we propose a flow-based reduction algorithm and a squeeze loss used in the training process. We evaluate our optimized network on various public MTL datasets and show ours achieves state-of-the-art performance. An extensive ablation study experimentally validates the effectiveness of the sub-module and schemes in our framework.

This paper presents a pioneering methodology, termed StructTuning, to efficiently transform foundation Large Language Models (LLMs) into domain specialists. It significantly minimizes the training corpus requirement to a mere 0.3% while achieving an impressive 50% of traditional knowledge injection performance. Our method is inspired by the educational processes for human students, particularly how structured domain knowledge from textbooks is absorbed and then applied to tackle real-world challenges through specific exercises. Based on this, we propose a novel two-stage knowledge injection strategy: Structure-aware Continual Pre-Training (SCPT) and Structure-aware Supervised Fine-Tuning (SSFT). In the SCPT phase, we organize the training data into an auto-generated taxonomy of domain knowledge, enabling LLMs to effectively memorize textual segments linked to specific expertise within the taxonomy's architecture. Subsequently, in the SSFT phase, we explicitly prompt models to reveal the underlying knowledge structure in their outputs, leveraging this structured domain insight to address practical problems adeptly. Our ultimate method has undergone extensive evaluations across model architectures and scales, using closed-book question-answering tasks on LongBench and MMedBench datasets. Remarkably, our method matches 50% of the improvement displayed by the state-of-the-art MMedLM2 on MMedBench, but with only 0.3% quantity of the training corpus. This breakthrough showcases the potential to scale up our StructTuning for stronger domain-specific LLMs. Code will be made public soon.

Optical multilayer thin film structures have been widely used in numerous photonic applications. However, existing inverse design methods have many drawbacks because they either fail to quickly adapt to different design targets, or are difficult to suit for different types of structures, e.g., designing for different materials at each layer. These methods also cannot accommodate versatile design situations under different angles and polarizations. In addition, how to benefit practical fabrications and manufacturing has not been extensively considered yet. In this work, we introduce OptoGPT (Opto Generative Pretrained Transformer), a decoder-only transformer, to solve all these drawbacks and issues simultaneously.

Prior work has shown that fine-tuning models on a narrow domain with misaligned data can lead to broad misalignment - a phenomenon termed "emergent misalignment" (Betley et al. 2025). While all tested models were susceptible to emergent misalignment, some models showed more resistance than others. Specifically the Qwen-2.5 family proved to be relatively resistant, while GPT-4o exhibited the strongest misalignment. In this paper we evaluate if current-generation open-weights models exhibit similar resistance to the Qwen-2.5 family and measure misalignment robustness over a range of model architectures and scales. We replicate the effect across nine modern open-weights models (Gemma 3 and Qwen 3 families, 1B-32B parameters). Models fine-tuned on insecure code generation show a 0.68% misalignment rate (compared to 0.07% for base models), matching the lower end of prior open-model results but dramatically lower than GPT-4o's 20%. We identify a critical format-dependent vulnerability: requiring JSON output doubles misalignment rates compared to natural language prompts (0.96% vs 0.42%). This suggests that structural constraints may bypass safety training by reducing the model's 'degrees of freedom' to refuse. These findings confirm emergent misalignment as a reproducible phenomenon in modern open-weights models, with rates substantially lower than observed in proprietary systems.

Modern computer vision pipelines handle large images in one of two sub-optimal ways: down-sampling or cropping. These two methods incur significant losses in the amount of information and context present in an image. There are many downstream applications in which global context matters as much as high frequency details, such as in real-world satellite imagery; in such cases researchers have to make the uncomfortable choice of which information to discard. We introduce xT, a simple framework for vision transformers which effectively aggregates global context with local details and can model large images end-to-end on contemporary GPUs. We select a set of benchmark datasets across classic vision tasks which accurately reflect a vision model's ability to understand truly large images and incorporate fine details over large scales and assess our method's improvement on them. By introducing a nested tokenization scheme for large images in conjunction with long-sequence length models normally used for natural language processing, we are able to increase accuracy by up to 8.6% on challenging classification tasks and F_1 score by 11.6 on context-dependent segmentation in large images.

Large Language Models (LLMs) have shown to be capable of various tasks, yet their capability in interpreting and reasoning over tabular data remains an underexplored area. In this context, this study investigates from three core perspectives: the robustness of LLMs to structural perturbations in tables, the comparative analysis of textual and symbolic reasoning on tables, and the potential of boosting model performance through the aggregation of multiple reasoning pathways. We discover that structural variance of tables presenting the same content reveals a notable performance decline, particularly in symbolic reasoning tasks. This prompts the proposal of a method for table structure normalization. Moreover, textual reasoning slightly edges out symbolic reasoning, and a detailed error analysis reveals that each exhibits different strengths depending on the specific tasks. Notably, the aggregation of textual and symbolic reasoning pathways, bolstered by a mix self-consistency mechanism, resulted in achieving SOTA performance, with an accuracy of 73.6% on WIKITABLEQUESTIONS, representing a substantial advancement over previous existing table processing paradigms of LLMs.

Large language models deliver strong reasoning and tool-use skills, yet their computational demands make them impractical for edge or cost-sensitive deployments. We present Xmodel-2.5, a 1.3-billion-parameter small language model designed as a drop-in agent core. Training with maximal-update parameterization (μP) allows hyper-parameters tuned on a 20M-parameter proxy to transfer directly to the full model, even under the parameter-tied tie-word-embedding architecture. A 1.4T-token Warmup--Stable--Decay curriculum is used, and we further show that switching from AdamW to Muon during the decay phase improves the 13-task reasoning average by 4.58\,\% while keeping every other hyper-parameter fixed, verifying that early AdamW stability can be paired with late Muon sharpening for better downstream performance. FP8-mixed-precision training balances accuracy and throughput. All checkpoints, recipes, and evaluation code are released under the Apache-2.0 license.https://huggingface.co/XiaoduoAILab/Xmodel-2.5 and https://huggingface.co/XiaoduoAILab/Xmodel-2.5-history (training checkpoints). Training code and evaluation harness: https://github.com/XiaoduoAILab/Xmodel-2.5.

We present preliminary results of the project OpenGPT-X. At present, the project has developed two multilingual LLMs designed to embrace Europe's linguistic diversity by supporting all 24 official languages of the European Union. Trained on a dataset comprising around 60% non-English data and utilizing a custom multilingual tokenizer, our models address the limitations of existing LLMs that predominantly focus on English or a few high-resource languages. We detail the models' development principles, data processing techniques, tokenizer optimization, and training methodologies. The models demonstrate competitive performance across multilingual benchmarks, as evidenced by its performance on European versions of ARC, HellaSwag, MMLU, and TruthfulQA.

The ability to accurately model the fitness landscape of protein sequences is critical to a wide range of applications, from quantifying the effects of human variants on disease likelihood, to predicting immune-escape mutations in viruses and designing novel biotherapeutic proteins. Deep generative models of protein sequences trained on multiple sequence alignments have been the most successful approaches so far to address these tasks. The performance of these methods is however contingent on the availability of sufficiently deep and diverse alignments for reliable training. Their potential scope is thus limited by the fact many protein families are hard, if not impossible, to align. Large language models trained on massive quantities of non-aligned protein sequences from diverse families address these problems and show potential to eventually bridge the performance gap. We introduce Tranception, a novel transformer architecture leveraging autoregressive predictions and retrieval of homologous sequences at inference to achieve state-of-the-art fitness prediction performance. Given its markedly higher performance on multiple mutants, robustness to shallow alignments and ability to score indels, our approach offers significant gain of scope over existing approaches. To enable more rigorous model testing across a broader range of protein families, we develop ProteinGym -- an extensive set of multiplexed assays of variant effects, substantially increasing both the number and diversity of assays compared to existing benchmarks.

In recent years, the application of transformer-based models in time-series forecasting has received significant attention. While often demonstrating promising results, the transformer architecture encounters challenges in fully exploiting the temporal relations within time series data due to its attention mechanism. In this work, we design eXponential Patch (xPatch for short), a novel dual-stream architecture that utilizes exponential decomposition. Inspired by the classical exponential smoothing approaches, xPatch introduces the innovative seasonal-trend exponential decomposition module. Additionally, we propose a dual-flow architecture that consists of an MLP-based linear stream and a CNN-based non-linear stream. This model investigates the benefits of employing patching and channel-independence techniques within a non-transformer model. Finally, we develop a robust arctangent loss function and a sigmoid learning rate adjustment scheme, which prevent overfitting and boost forecasting performance. The code is available at the following repository: https://github.com/stitsyuk/xPatch.

Much recent progress in applications of machine learning models to NLP has been driven by benchmarks that evaluate models across a wide variety of tasks. However, these broad-coverage benchmarks have been mostly limited to English, and despite an increasing interest in multilingual models, a benchmark that enables the comprehensive evaluation of such methods on a diverse range of languages and tasks is still missing. To this end, we introduce the Cross-lingual TRansfer Evaluation of Multilingual Encoders XTREME benchmark, a multi-task benchmark for evaluating the cross-lingual generalization capabilities of multilingual representations across 40 languages and 9 tasks. We demonstrate that while models tested on English reach human performance on many tasks, there is still a sizable gap in the performance of cross-lingually transferred models, particularly on syntactic and sentence retrieval tasks. There is also a wide spread of results across languages. We release the benchmark to encourage research on cross-lingual learning methods that transfer linguistic knowledge across a diverse and representative set of languages and tasks.

Genomic language models (gLMs) have shown mostly modest success in identifying evolutionarily constrained elements in mammalian genomes. To address this issue, we introduce a novel framework for training gLMs that explicitly models nucleotide evolution on phylogenetic trees using multispecies whole-genome alignments. Our approach integrates an alignment into the loss function during training but does not require it for making predictions, thereby enhancing the model's applicability. We applied this framework to train PhyloGPN, a model that excels at predicting functionally disruptive variants from a single sequence alone and demonstrates strong transfer learning capabilities.

Deploying models on target domain data subject to distribution shift requires adaptation. Test-time training (TTT) emerges as a solution to this adaptation under a realistic scenario where access to full source domain data is not available and instant inference on target domain is required. Despite many efforts into TTT, there is a confusion over the experimental settings, thus leading to unfair comparisons. In this work, we first revisit TTT assumptions and categorize TTT protocols by two key factors. Among the multiple protocols, we adopt a realistic sequential test-time training (sTTT) protocol, under which we further develop a test-time anchored clustering (TTAC) approach to enable stronger test-time feature learning. TTAC discovers clusters in both source and target domain and match the target clusters to the source ones to improve generalization. Pseudo label filtering and iterative updating are developed to improve the effectiveness and efficiency of anchored clustering. We demonstrate that under all TTT protocols TTAC consistently outperforms the state-of-the-art methods on six TTT datasets. We hope this work will provide a fair benchmarking of TTT methods and future research should be compared within respective protocols. A demo code is available at https://github.com/Gorilla-Lab-SCUT/TTAC.

With the rapid growth in the use of fine-tuning for large language models (LLMs), optimizing fine-tuning while keeping inference efficient has become highly important. However, this is a challenging task as it requires improvements in all aspects, including inference speed, fine-tuning speed, memory consumption, and, most importantly, model quality. Previous studies have attempted to achieve this by combining quantization with fine-tuning, but they have failed to enhance all four aspects simultaneously. In this study, we propose a new lightweight technique called Quantization for Efficient Fine-Tuning (QEFT). QEFT accelerates both inference and fine-tuning, is supported by robust theoretical foundations, offers high flexibility, and maintains good hardware compatibility. Our extensive experiments demonstrate that QEFT matches the quality and versatility of full-precision parameter-efficient fine-tuning, while using fewer resources. Our code is available at https://github.com/xvyaward/qeft.

Recent Large Reasoning Models (LRMs) with thinking traces have shown strong performance on English reasoning tasks. However, their ability to think in other languages is less studied. This capability is as important as answer accuracy for real world applications because users may find the reasoning trace useful for oversight only when it is expressed in their own language. We comprehensively evaluate two leading families of LRMs on our XReasoning benchmark and find that even the most advanced models often revert to English or produce fragmented reasoning in other languages, revealing a substantial gap in multilingual reasoning. Prompt based interventions that force models to reason in the users language improve readability and oversight but reduce answer accuracy, exposing an important trade off. We further show that targeted post training on just 100 examples mitigates this mismatch, though some accuracy loss remains. Our results highlight the limited multilingual reasoning capabilities of current LRMs and outline directions for future work. Code and data are available at https://github.com/Betswish/mCoT-XReasoning.

In this note we establish a 1-to-1 correspondence between the class of generalized quadrangles with ovoids and the class of balanced incomplete block designs that posses a non-triangular local resolution system and have the appropriate parameters. We present a non-triangular local resolution system for a difference family BIBD construction of Sprott.

Scientific researchers frequently use the in situ synchrotron high-energy powder X-ray diffraction (XRD) technique to examine the crystallographic structures of materials in functional devices such as rechargeable battery materials. We propose a method for identifying artifacts in experimental XRD images. The proposed method uses deep learning convolutional neural network architectures, such as tunable U-Nets to identify the artifacts. In particular, the predicted artifacts are evaluated against the corresponding ground truth (manually implemented) using the overall true positive rate or recall. The result demonstrates that the U-Nets can consistently produce great recall performance at 92.4% on the test dataset, which is not included in the training, with a 34% reduction in average false positives in comparison to the conventional method. The U-Nets also reduce the time required to identify and separate artifacts by more than 50%. Furthermore, the exclusion of the artifacts shows major changes in the integrated 1D XRD pattern, enhancing further analysis of the post-processing XRD data.