Why Do Video Diffusion Models Violate Physics? Unveiling the Flaws in Attention Mechanisms
Paper • 2609.23658 • Published • 11
AI & ML interests
Natural Language Processing, Multimodal Information Processing
Recent Activity
View all activity
Papers
Why Do Video Diffusion Models Violate Physics? Unveiling the Flaws in Attention Mechanisms
Reading Images Like Texts: Sequential Image Understanding in Vision-Language Models
paulsmith0217Â
authored a
paper 1 day ago
paulsmith0217Â
submitted a
paper to Daily Papers 1 day ago
paulsmith0217Â
authored 4
papers 2 days ago
Reading Images Like Texts: Sequential Image Understanding in Vision-Language Models
Paper • 2509.19191 • Published • 1
ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools
Paper • 2406.12793 • Published • 35
Seedance 2.0: Advancing Video Generation for World Complexity
Paper • 2604.14148 • Published • 171
ChatGLM-Math: Improving Math Problem-Solving in Large Language Models with a Self-Critique Pipeline
Paper • 2404.02893 • Published • 21
paulsmith0217Â
updated a
Space 2 days ago
paulsmith0217Â
published a
Space 2 days ago