Three things everyone should know about Vision Transformers Paper • 2203.09795 • Published Mar 18, 2022 • 1
Rethinking Vision Transformer Depth via Structural Reparameterization Paper • 2511.19718 • Published Nov 24, 2025 • 1
Finite Scalar Quantization Enables Redundant and Transmission-Robust Neural Audio Compression at Low Bit-rates Paper • 2509.09550 • Published Sep 11, 2025 • 4
Reasoning as Compression: Unifying Budget Forcing via the Conditional Information Bottleneck Paper • 2603.08462 • Published Mar 9 • 22
The Y-Combinator for LLMs: Solving Long-Context Rot with λ-Calculus Paper • 2603.20105 • Published 26 days ago • 37
Context Adaptive Extended Chain Coding for Semantic Map Compression Paper • 2603.03073 • Published Mar 3 • 1
Challenges and Research Directions for Large Language Model Inference Hardware Paper • 2601.05047 • Published Jan 8 • 1
ACC-UNet: A Completely Convolutional UNet model for the 2020s Paper • 2308.13680 • Published Aug 25, 2023 • 1
Flash-VAED: Plug-and-Play VAE Decoders for Efficient Video Generation Paper • 2602.19161 • Published Feb 22 • 1
Dataset Distillation via Relative Distribution Matching and Cognitive Heritage Paper • 2602.05391 • Published Feb 5 • 1