Hugging Face Papers ↗ · 2026-11-17
Out of Sight, Still in Mind: Token Compression for Omni-LLMs
Media reports Hugging Face Papers Source language: Chinese
ReMo is a training-free method that reduces inference input token costs for omni-modal large language models by compressing redundant visual tokens through cross-modal alignment and replacing object-level visual tokens with compact text descriptions, while maintaining comparable accuracy on audio-visual tasks.
Full text
ReMo, a training-free method, reduces inference input token cost for omni-modal large language models by compressing redundant visual tokens through cross-modal alignment and replacing object-level visual tokens with compact text descriptions, achieving comparable accuracy on audio-visual tasks.