WaveZip: Wavelet-Driven Space-Time Decoupling for Video Token Condensation Paper • 2607.23265 • Published Aug 3 • 1
Duplex-MPE: Benchmarking Multi-Party Interaction in Full-Duplex Dialogue Paper • 2609.31948 • Published 15 days ago • 89
SpecEyes: Accelerating Agentic Multimodal LLMs via Speculative Perception and Planning Paper • 2603.23483 • Published Mar 24 • 62
SocialOmni: Benchmarking Audio-Visual Social Interactivity in Omni Models Paper • 2603.16859 • Published Mar 17 • 48