About this paper
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.
The goal of this paper is to reduce the input token cost of Omni-modal large language models (Omni-LLMs) at inference time. Omni-LLMs reason jointly over audio, video and text, but the cost of the three streams is highly unbalanced: visual tokens account for the vast majority of the input, and are highly redundant. In this paper, we propose ReMo, a training-free framework that compresses visual tokens by redistributing their information across modalities: a visual token is kept only if its information appears nowhere else. ReMo achieves this in two ways: (i) it aligns audio and video in a shared space via closed-form calibration, and removes visual tokens already explained by the audio or…
Omni-modal large language modelsOmni-LLMstraining-free frameworkvisual token compressioncross-modal information redistributionclosed-form calibrationaudio-video alignmentshared spaceobject-level visual tokenslightweight object detector
- Upvotes
- 3
- Authors
- 4
- Published
- Nov 17, 2026
Summary and abstract excerpt via Hugging Face Papers ↗ · arXiv.
Trending history
Out of Sight, Still in Mind: Token Compression for Omni-LLMs was first seen on Hugging Face · Daily papers on Nov 19, 2026. Since then it has appeared in 2 checks on 1 different day. Its best position was #28 of 30, reached on Nov 19, 11:29 UTC. It dropped off the list after Nov 19, 13:29 UTC.