CreFlow: Corrective Reflow for Sparse-Reward Embodied Video Diffusion RL

Documenti analoghi

• Enhancing Inverse Reinforcement Learning through Encoding Dynamic Information in Reward Shaping
  di: Zhan, Simon Sinong, et al.
  Pubblicazione: (2024)
• CoMAS: Co-Evolving Multi-Agent Systems via Interaction Rewards
  di: Xue, Xiangyuan, et al.
  Pubblicazione: (2025)
• Empowering Autonomous Driving with Large Language Models: A Safety Perspective
  di: Wang, Yixuan, et al.
  Pubblicazione: (2023)
• Training-Free Adaptation of Diffusion Models via Doob's $h$-Transform
  di: Zhu, Qijie, et al.
  Pubblicazione: (2026)
• ProReflow: Progressive Reflow with Decomposed Velocity
  di: Ke, Lei, et al.
  Pubblicazione: (2025)