OmniZip: Audio-Guided Dynamic Token Compression for Fast Omnimodal Large Language Models Paper • 2511.14582 • Published 14 days ago • 17
Which Heads Matter for Reasoning? RL-Guided KV Cache Compression Paper • 2510.08525 • Published Oct 9 • 22
OBS-Diff: Accurate Pruning For Diffusion Models in One-Shot Paper • 2510.06751 • Published Oct 8 • 21
AutoDroid-V2: Boosting SLM-based GUI Agents via Code Generation Paper • 2412.18116 • Published Dec 24, 2024 • 1