Reasoning Physical Video Generation with Diffusion Timestep Tokens via Reinforcement Learning

Documenti analoghi

• Generative Multimodal Pretraining with Discrete Diffusion Timestep Tokens
  di: Pan, Kaihang, et al.
  Pubblicazione: (2025)
• Selftok: Discrete Visual Tokens of Autoregression, by Diffusion, and for Reasoning
  di: Wang, Bohan, et al.
  Pubblicazione: (2025)
• Few-shot Learner Parameterization by Diffusion Time-steps
  di: Yue, Zhongqi, et al.
  Pubblicazione: (2024)
• AnyEdit: Mastering Unified High-Quality Image Editing for Any Idea
  di: Yu, Qifan, et al.
  Pubblicazione: (2024)
• Layer- and Timestep-Adaptive Differentiable Token Compression Ratios for Efficient Diffusion Transformers
  di: You, Haoran, et al.
  Pubblicazione: (2024)