Out of Sight, Still in Mind: Token Compression for Omni-LLMs A new research paper targets the input token cost of omni-modal large language models (Omni-LLMs) at inference time, noting that visual tokens account for the vast majority of input and are highly unbalanced against audio and text streams. The work proposes token compression for Omni-LLMs that reason jointly over audio, video and text, aiming to cut the cost of the dominant visual stream. 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 h