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

OmniMem: Perturbation-aware Memory Compression for Streaming Audio-Visual LLMs arXiv:2606.07577v1 Announce Type: cross 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. We present OmniMem, a memory-efficient streaming framework designed specifically for audio-visual LLMs. Unlike existing compression methods that treat al