VideoREPA: Learning Physics for Video Generation through Relational Alignment with Foundation Models

Documenti analoghi

• PCP-MAE: Learning to Predict Centers for Point Masked Autoencoders
  di: Zhang, Xiangdong, et al.
  Pubblicazione: (2024)
• Towards More Diverse and Challenging Pre-training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Views
  di: Zhang, Xiangdong, et al.
  Pubblicazione: (2025)
• Towards World Simulator: Crafting Physical Commonsense-Based Benchmark for Video Generation
  di: Meng, Fanqing, et al.
  Pubblicazione: (2024)
• Dual-Branch Center-Surrounding Contrast: Rethinking Contrastive Learning for 3D Point Clouds
  di: Zhang, Shaofeng, et al.
  Pubblicazione: (2025)
• DreamWorld: Unified World Modeling in Video Generation
  di: Tan, Boming, et al.
  Pubblicazione: (2026)