activity
20242026
collaborators

9 papers

cs.CV2026

High-Entropy Tokens as Multimodal Failure Points in Vision-Language Models

Mengqi He, Xinyu Tian, Xin Shen +4

Vision-language models (VLMs) achieve remarkable performance but remain vulnerable to adversarial attacks. Entropy, as a measure of model uncertainty, is highly correlated with VLM…

cs.CV2026

All Roads Lead to Rome: Incentivizing Divergent Thinking in Vision-Language Models

Xinyu Tian, Shu Zou, Zhaoyuan Yang +3

Recent studies have demonstrated that Reinforcement Learning (RL), notably Group Relative Policy Optimization (GRPO), can intrinsically elicit and enhance the reasoning capabilitie…

cs.CV2026

More Thought, Less Accuracy? On the Dual Nature of Reasoning in Vision-Language Models

Xinyu Tian, Shu Zou, Zhaoyuan Yang +5

Reasoning has emerged as a pivotal capability in Large Language Models (LLMs). Through Reinforcement Learning (RL), typically Group Relative Policy Optimization (GRPO), these model…

cs.CV2025

Unlocking Vision-Language Models for Video Anomaly Detection via Fine-Grained Prompting

Shu Zou, Xinyu Tian, Lukas Wesemann +3

Prompting has emerged as a practical way to adapt frozen vision-language models (VLMs) for video anomaly detection (VAD). Yet, existing prompts are often overly abstract, overlooki…

cs.CV2025

Probability Density Geodesics in Image Diffusion Latent Space

Qingtao Yu, Jaskirat Singh, Zhaoyuan Yang +5

Diffusion models indirectly estimate the probability density over a data space, which can be used to study its structure. In this work, we show that geodesics can be computed in di…

cs.CV2025

Identifying and Mitigating Position Bias of Multi-image Vision-Language Models

Xinyu Tian, Shu Zou, Zhaoyuan Yang +1

The evolution of Large Vision-Language Models (LVLMs) has progressed from single to multi-image reasoning. Despite this advancement, our findings indicate that LVLMs struggle to ro…