Zhang Wan — accepted AI-conference papers

2026

Video-SVD: Efficient Video Diffusion via Orthogonal Basis Composition

Zhang Wan, Yu Li, Tianze Huang, Haochen Li, Juan Cao, Sheng Tang

ICML 2026poster

Video Diffusion Transformers (VDiTs) represent the state-of-the-art in video generation but are fundamentally constrained by the quadratic computational complexity of self-attention. To accelerate this critical computation, we analyze the pre-softmax matrix ($QK^T$) and reveal two key insights: (1) …

Cited by 0 Source ↗Scholar ↗

2026

You Don't Protect if You Don't Expect: Breaking the Key Assumption behind CLIP's Test-Time Defenses

Ruize Zhang, Yu Li, Zhang Wan, Juan Cao, Jie Zhang, Sheng Tang

ICML 2026poster

Recent test-time defenses for CLIP claim to preserve zero-shot clean accuracy while improving adversarial robustness. However, we find the reported robustness of six recent proposed state-of-the-art methods substantially overestimated: they fail under basic adaptive attacks. We further observe that …

Cited by 0 Source ↗Scholar ↗