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.

Sources

← Back to Daily AI Report