Zhuo-Xu Cui

Cosmos-Eval: Towards Explainable Evaluation of Physics and Semantics in Text-to-Video Models

White-Box Prompt Transformers: Variationally Grounded Prompt–Attention Coupling for Unified Image Restoration

Quantifying Information Flow in Diffusion Models: Entropy-Guided Noise Scheduling and Mutual Information Evaluation

DualCnst: Enhancing Zero-Shot Out-of-Distribution Detection via Text-Image Consistency in Vision-Language Models

Text-Image Dual Consistency-Guided OOD Detection with Pretrained Vision-Language Models