OmniZip: Audio-Guided Dynamic Token Compression for Fast Omnimodal Large Language Models Paper • 2511.14582 • Published 22 days ago • 17
MergeMix: A Unified Augmentation Paradigm for Visual and Multi-Modal Understanding Paper • 2510.23479 • Published Oct 27 • 14
OBS-Diff: Accurate Pruning For Diffusion Models in One-Shot Paper • 2510.06751 • Published Oct 8 • 21
Which Heads Matter for Reasoning? RL-Guided KV Cache Compression Paper • 2510.08525 • Published Oct 9 • 22