D$^2$-World: An Efficient World Model through Decoupled Dynamic Flow

Documenti analoghi

• An Efficient Occupancy World Model via Decoupled Dynamic Flow and Image-assisted Training
  di: Zhang, Haiming, et al.
  Pubblicazione: (2024)
• DLWM: Dual Latent World Models enable Holistic Gaussian-centric Pre-training in Autonomous Driving
  di: Zhu, Yiyao, et al.
  Pubblicazione: (2026)
• SQS: Enhancing Sparse Perception Models via Query-based Splatting in Autonomous Driving
  di: Zhang, Haiming, et al.
  Pubblicazione: (2025)
• Benchmarking the Robustness of LiDAR Semantic Segmentation Models
  di: Yan, Xu, et al.
  Pubblicazione: (2023)
• WPT: World-to-Policy Transfer via Online World Model Distillation
  di: Jiang, Guangfeng, et al.
  Pubblicazione: (2025)