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.CV2026-07-22

Look Less, Think Faster: Joint Token-Compute Adaptation for Multimodal LLMs

Pengcheng Wang, Zhiquan Wang, Jayoung Lee, Zhuoyan Xu, Ran Xu, Saurabh Bagchi, et al.

Multimodal Large Language Models (MLLMs) have recently demonstrated strong performance across vision-language tasks. However, their high inference cost, arising from both the large number of input visual tokens and the heavy computation of the large language model (LLM), remains…

View free PDFSource page
arxivcs.CVcs.SE2026-07-31

CodeShrink: Adaptive Visual Compression for Efficient Multimodal Code Understanding

Wenxin Tang, Jingyu Xiao, Zhenyu Liu, Zipeng Xie, Junliang Liu, Wang Luo, et al.

Rendering source code as images offers a promising way to reduce the input costs of Multimodal Large Language Models (MLLMs). Adjusting image resolution can trade visual token cost against content fidelity. However, resolution scaling alone overlooks two sources of inefficiency:…

View free PDFSource page
arxivcs.SEcs.AIcs.CV2026-07-23

Pixels for Programs? A Cross-Provider Case Study of Input-Token Accounting for Source Code as Text and Images

Ronak Bhalgami

Long source-code contexts consume many text tokens, motivating the proposal to render code as images for vision-language models. Recent work asks whether models can still solve code tasks after this transformation. We examine a different systems question: how commercial APIs coun…

View free PDFSource page
arxivcs.CV2026-07-23

C-PTQ: Fisher-weighted Channel-wise Sensitivity for Post-training Quantization of MLLMs

Jiameng Li, Han Zhou, Matthew B. Blaschko

Multimodal large language models (MLLMs) require huge memory and computational costs, which limits their practical deployment. Post-training quantization (PTQ) techniques offer an efficient solution for model compression and inference acceleration. Yet, the quantized model faces…

View free PDFSource page
arxivcs.CVcs.CLcs.LG2026-07-24

Small Vision-Language Models Know When They Are Wrong But Cannot Say So: A Two-Model Study of Stated versus Internal Confidence Under Realistic Image Degradation

M M Asif Ferdous

Vision-language models (VLMs) are increasingly deployed on consumer hardware where input images are degraded by compression, camera shake, and poor lighting. In such settings, a reliable uncertainty signal matters more than raw accuracy, because it determines when a system should…

View free PDFSource page