AI RESEARCH
ZeroSense:How Vision matters in Long Context Compression
arXiv CS.CV
•
ArXi:2603.11846v1 Announce Type: new Recent visual-text compression (VTC) methods, typified by DeepSeek-OCR, report impressive high token compression ratios for long-context modeling tasks by leveraging text-to-image rendering. However, existing evaluation protocols heavily rely on downstream task performance. Such evaluation metrics fail to accurately measure text preservation due to the strong inherent linguistic priors of Multimodal Large Language Models (MLLMs). In this work, we