Fabio Rollo's picture

Fabio Rollo

fabiodr

·

AI & ML interests

LLMs, Computer Vision, Physics Simulation, Image synthesis

Recent Activity

liked a model about 19 hours ago

ByteDance/Ouro-2.6B-Thinking

liked a model 1 day ago

lmstudio-community/gemma-4-31B-it-GGUF

liked a model 1 day ago

mlx-community/gemma-4-31b-it-4bit

View all activity

Organizations

None yet

upvoted a collection 1 day ago

Gemma 4

64 items • Updated 9 days ago • 96

upvoted an article 5 days ago

Article

Falcon Perception

11 days ago

•

44

upvoted an article 9 days ago

Article

Welcome Gemma 4: Frontier multimodal intelligence on device

+5

10 days ago

•

819

upvoted 2 collections 9 days ago

TranslateGemma

3 items • Updated about 1 month ago • 232

Gemma 4

8 items • Updated 9 days ago • 567

upvoted a paper 10 days ago

MJ1: Multimodal Judgment via Grounded Verification

Paper • 2603.07990 • Published Mar 9 • 1

upvoted an article 11 days ago

Article

TRL v1.0: Post-Training Library Built to Move with the Field

+2

12 days ago

•

47

upvoted 2 articles 12 days ago

Article

Training and Finetuning Reranker Models with Sentence Transformers v4

Mar 26, 2025

•

188

Article

Transformers.js v4: Now Available on NPM!

Feb 9

•

92

upvoted a collection 12 days ago

Transformers.js V4 demos

A collection of demos built with Transformers.js V4 • 23 items • Updated 3 days ago • 50

upvoted a paper 16 days ago

The Y-Combinator for LLMs: Solving Long-Context Rot with λ-Calculus

Paper • 2603.20105 • Published 22 days ago • 37

upvoted a collection 22 days ago

CodeScout

RL-trained code search agents (1.7B, 4B, 14B) that outperform 2–18× larger models using only a Unix terminal. 📄 arxiv.org/abs/2603.17829 • 12 items • Updated 24 days ago • 7

upvoted 4 collections 29 days ago

PyLate 🐕

State-of-the-art late interaction models trained using PyLate • 5 items • Updated 5 days ago • 4

ColBERT-Zero 🐶

First large-scale fully pre-trained ColBERT model using only public data, outperforming GTE-ModernColBERT and GTE-ModernBERT • 10 items • Updated 5 days ago • 20

👁️ LFM2.5-VL

13 items • Updated 3 days ago • 34

💧 LFM2.5

Collection of post-trained and base LFM2.5 models. • 30 items • Updated 3 days ago • 124

upvoted a collection 30 days ago

LateOn-Code 💻

State-of-the-art late interaction code retrieval models • 6 items • Updated 5 days ago • 17

upvoted an article 30 days ago

Article

LateOn-Code & ColGrep: LightOn unveils state-of-the-art code retrieval models and code search tooling

Feb 12

•

53

upvoted an article about 2 months ago

Article

ColBERT-Zero: To Pre-train Or Not To Pre-train ColBERT models?

Feb 19

•

19

upvoted a paper 2 months ago

SWE-Universe: Scale Real-World Verifiable Environments to Millions

Paper • 2602.02361 • Published Feb 2 • 60