Harness Local Rewards for Global Benefits: Effective Text-to-Video Generation Alignment with Patch-level Reward Models

Documenti analoghi

• Nabla-R2D3: Effective and Efficient 3D Diffusion Alignment with 2D Rewards
  di: Liu, Qingming, et al.
  Pubblicazione: (2025)
• GraphShaper: Geometry-aware Alignment for Improving Transfer Learning in Text-Attributed Graphs
  di: Zhang, Heng, et al.
  Pubblicazione: (2025)
• CAD-Coder: Text-to-CAD Generation with Chain-of-Thought and Geometric Reward
  di: Guan, Yandong, et al.
  Pubblicazione: (2025)
• LumiGen: An LVLM-Enhanced Iterative Framework for Fine-Grained Text-to-Image Generation
  di: Dong, Xiaoqi, et al.
  Pubblicazione: (2025)
• FlexControl: Computation-Aware ControlNet with Differentiable Router for Text-to-Image Generation
  di: Fang, Zheng, et al.
  Pubblicazione: (2025)