5 papers
Same Semantics, Different Paths: Self-Improving Alignment for Vision-Text Compression
Tianyu Liang, Xiangxi Zheng, Yilin Wang +1
Vision-Text Compression (VTC) renders long texts into images and encodes them through the vision encoder (ViT), compressing thousands of text tokens into far fewer visual tokens. H…
Efficient Frame Selection for Long Videos at Test Time with Attention-Based MLLM Selectors
Yilin Wang, Xiangxi Zheng, Dongxing Mao +6
Understanding long videos with multimodal large language models (MLLMs) requires selecting a compact set of frames from thousands of candidates, yet identifying the right frames se…
CharTide: Data-Centric Chart-to-Code Generation via Tri-Perspective Tuning and Inquiry-Driven Evolution
Xiangxi Zheng, Kuang He, Jiayi Hu +6
Chart-to-code generation demands strict visual precision and syntactic correctness from Vision-Language Models (VLMs). However, existing approaches are fundamentally constrained by…
Seeing is Not Reasoning: MVPBench for Graph-based Evaluation of Multi-path Visual Physical CoT
Zhuobai Dong, Junchao Yi, Ziyuan Zheng +5
Understanding the physical world - governed by laws of motion, spatial relations, and causality - poses a fundamental challenge for multimodal large language models (MLLMs). While…
V-MAGE: A Game Evaluation Framework for Assessing Vision-Centric Capabilities in Multimodal Large Language Models
Xiangxi Zheng, Linjie Li, Zhengyuan Yang +5
Recent advancements in Multimodal Large Language Models (MLLMs) have demonstrated impressive capabilities in visual-text processing. However, existing static image-text benchmarks…