5 papers
Deep Pre-Alignment for VLMs
Tianyu Yu, Kechen Fang, Zihao Wan +5
Most Vision Language Models (VLMs) directly map outputs from ViT encoders to the LLM via a lightweight projector. While effective, recent analysis suggests this architecture suffer…
Enabling Stroke-Level Structural Analysis of Hieroglyphic Scripts without Language-Specific Priors
Fuwen Luo, Zihao Wan, Ziyue Wang +6
Hieroglyphs, as logographic writing systems, encode rich semantic and cultural information within their internal structural composition. Yet, current advanced Large Language Models…
Bridging Vision, Language, and Mathematics: Pictographic Character Reconstruction with Bézier Curves
Zihao Wan, Pau Tong Lin Xu, Fuwen Luo +3
While Vision-language Models (VLMs) have demonstrated strong semantic capabilities, their ability to interpret the underlying geometric structure of visual information is less expl…
StreamingBench: Assessing the Gap for MLLMs to Achieve Streaming Video Understanding
Junming Lin, Zheng Fang, Chi Chen +5
The rapid development of Multimodal Large Language Models (MLLMs) has expanded their capabilities from image comprehension to video understanding. However, most of these MLLMs focu…
CODIS: Benchmarking Context-Dependent Visual Comprehension for Multimodal Large Language Models
Fuwen Luo, Chi Chen, Zihao Wan +11
Multimodal large language models (MLLMs) have demonstrated promising results in a variety of tasks that combine vision and language. As these models become more integral to researc…