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 28 days ago • 21
The Y-Combinator for LLMs: Solving Long-Context Rot with λ-Calculus Paper • 2603.20105 • Published 17 days ago • 36
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
Quant VideoGen: Auto-Regressive Long Video Generation via 2-Bit KV-Cache Quantization Paper • 2602.02958 • Published Feb 3 • 34
FluxMem: Adaptive Hierarchical Memory for Streaming Video Understanding Paper • 2603.02096 • Published Mar 2 • 1
Beyond Language Modeling: An Exploration of Multimodal Pretraining Paper • 2603.03276 • Published Mar 3 • 102