4 papers
The Invisible Hand of Physics: When Video Diffusion Models Know More Than They Show
Parsa Esmati, Somjit Nath, Katja Hofmann +3
Modern video diffusion models generate increasingly realistic and temporally coherent videos, motivating their use as candidate world simulators. Yet it remains unclear whether the…
Probability-Conserving Flow Guidance
Parsa Esmati, Junha Hyung, Amirhossein Dadashzadeh +2
Diffusion and flow-based generative models dominate visual synthesis, with guidance aligning samples to user input and improving perceptual quality. However, Classifier-Free Guidan…
Co-STAR: Collaborative Curriculum Self-Training with Adaptive Regularization for Source-Free Video Domain Adaptation
Amirhossein Dadashzadeh, Parsa Esmati, Majid Mirmehdi
Recent advances in Source-Free Unsupervised Video Domain Adaptation (SFUVDA) leverage vision-language models to enhance pseudo-label generation. However, challenges such as noisy p…
SEA: State-Exchange Attention for High-Fidelity Physics Based Transformers
Parsa Esmati, Amirhossein Dadashzadeh, Vahid Goodarzi +2
Current approaches using sequential networks have shown promise in estimating field variables for dynamical systems, but they are often limited by high rollout errors. The unresolv…