5 papers
Beyond Atomic Layouts: Compositional Design Understanding with Vision-Language Models
Yiyang Huang, Zhaowen Wang, Simon Jenni +4
Layout understanding, or the interpretation of element organization, is essential for document analysis, user interface (UI) creation, and graphic design. While recent vision-langu…
Distorted or Fabricated? A Survey on Hallucination in Video LLMs
Yiyang Huang, Yitian Zhang, Yizhou Wang +4
Despite significant progress in video-language modeling, hallucinations remain a persistent challenge in Video Large Language Models (Vid-LLMs), referring to outputs that appear pl…
Rethinking Fine-Tuning: Unlocking Hidden Capabilities in Vision-Language Models
Mingyuan Zhang, Yue Bai, Yifan Wang +2
Fine-tuning has become the dominant paradigm for adapting Vision-Language Models (VLMs), yet most approaches rely on explicit weight updates that introduce a fundamental trade-off.…
D-CoDe: Scaling Image-Pretrained VLMs to Video via Dynamic Compression and Question Decomposition
Yiyang Huang, Yizhou Wang, Yun Fu
Video large language models (Vid-LLMs), which excel in diverse video-language tasks, can be effectively constructed by adapting image-pretrained vision-language models (VLMs). Howe…
SHIELD: Suppressing Hallucinations In LVLM Encoders via Bias and Vulnerability Defense
Yiyang Huang, Liang Shi, Yitian Zhang +2
Large Vision-Language Models (LVLMs) excel in diverse cross-modal tasks. However, object hallucination, where models produce plausible but inaccurate object descriptions, remains a…