AI RESEARCH
OmniRefine: Alignment-Aware Cooperative Compression for Efficient Omnimodal Large Language Models
arXiv CS.AI
•
ArXi:2605.12056v1 Announce Type: new Omnimodal large language models (Omni-LLMs) show strong capability in audio-video understanding, but their practical deployment remains limited by high inference cost of long video streams and dense audio sequences. Despite recent progress, existing compression methods for Omni-LLMs typically rely on fixed or native compression units, which can disrupt cross-modal correspondence and the complementary information required for audio-video reasoning, making it difficult to improve inference efficiency while stably preserving performance.