Skip to content
Sagan

Paper

OmniMem: Perturbation-aware Memory Compression for Streaming Audio-Visual LLMs

Unreadunread

AI summary

arXiv:2606. 07577v1 Announce Type: new Abstract: Audio-visual large language models (LLMs) hold strong promise for long-form video understanding, yet their long-video inference is fundamentally limited by the linear growth of video tokens and key-value (KV) caches.