CORTEXA
← Browse
arxivcs.CV2026-07-23

Out of Sight, Still in Mind: Token Compression for Omni-LLMs

Suho Yoo, Youngjoon Jang, Hyebin Cho, Joon Son Chung

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 common embedding space, and removes visual tokens already explained by the audio or by other visual tokens; and (ii) it replaces object-level visual tokens with compact text proxies, short descriptions of each object and its location, conveying the same content in far fewer tokens. On Qwen2.5-Omni at two model scales, ReMo removes 54% of the input tokens with no loss in accuracy. Indeed, it slightly exceeds the full-token model, reaching 101.2% and 101.3% of its average accuracy over five audio-visual benchmarks.

View free PDFSource page

Related papers

arxivcs.LGcs.AIcs.CVcs.SD2026-07-03

OmniFocus: Query-Guided Modality-Balanced Token Compression for Omni-Modal Large Language Models

Shijie Cao, Qingyu Zhang, Boxi Yu, Yuzhong Zhang, Boxi Cao, Yaojie Lu, et al.

Omni modal large language models (OmniLLMs) have attracted wide attention for their ability to jointly process audio and video, but they generate large token sequences under audio-visual inputs, leading to substantial inference cost. Existing audio-visual token compression method…

View free PDFSource page
arxivcs.CV2026-07-02

When Token Compression Breaks: Structural Pruning vs. Token Reduction for Robust ViT Segmentation under High Compression

Tien-Phat Nguyen, Ngai-Man Cheung

Vision Transformers (ViTs) are strong backbones for semantic segmentation, but their computational cost limits deployment. Recent token compression methods for efficient transformer-based segmentation reduce this cost by decreasing the number of tokens. However, existing evaluati…

View free PDFSource page
arxivcs.CV2026-07-10

GeoTrace: Geometry-Aware Trajectory Token Compression for Video Large Language Models

Guohuan Xie, Mengqi Lei, Chuan Shi, Wei Bao, Yue Gao, Siqi Li

Although Video Large Language Models (Video LLMs) have shown strong performance in video understanding, their efficiency is still limited by the large number of visual tokens. Existing video token compression methods typically rely on frame-wise saliency or heuristic token mergin…

View free PDFSource page
arxivcs.CV2026-07-14

VisCo: Leveraging Large Language Models as Intrinsic Encoders for Visual Token Compression

Yupeng Zheng, Kai Zou, Bin Liu, Nenghai Yu

Vision-language models (VLMs) process large numbers of visual tokens, resulting in substantial inference latency and memory overhead. This has motivated extensive research on visual token compression. While training-free strategies rely on heuristic metrics and suffer significant…

View free PDFSource page
arxivcs.CV2026-07-10

Beyond Time Shifts: Adapting Omni-LLM as a Reference-Free Evaluator for Generative Audio-Visual Models

Yijie Qian, Juncheng Wang, Chao Xu, Huihan Wang, Yuxiang Feng, Yang Liu, et al.

As audio-visual generative models evolve into world simulators, cross-modal synchronization stands as a critical proxy for assessing the consistency of world dynamics and causality in generated content. However, existing evaluation metrics presume structural correctness, reducing…

View free PDFSource page
arxivcs.CV2026-07-09

LUMI: Tokenizer-Agnostic LLM-Based Lossless Image Compression

Chris Xing Tian, Chengkai Wu, Ziyu Wang, Rongqun Lin, Kecheng Chen, Xiandong Meng, et al.

Large language model (LLM)-based lossless image compression methods typically represent pixel data through the native text interface of a pretrained model, converting pixel values into token sequences that the LLM processes through its vocabulary head. This design shows that pret…

View free PDFSource page