Compositional Generative Modeling: A Single Model is Not All You Need

Documenti analoghi

• From Pixels to Predicates: Learning Symbolic World Models via Pretrained Vision-Language Models
  di: Athalye, Ashay, et al.
  Pubblicazione: (2024)
• Grounding Video Models to Actions through Goal Conditioned Exploration
  di: Luo, Yunhao, et al.
  Pubblicazione: (2024)
• DiMSam: Diffusion Models as Samplers for Task and Motion Planning under Partial Observability
  di: Fang, Xiaolin, et al.
  Pubblicazione: (2023)
• AdaWorld: Learning Adaptable World Models with Latent Actions
  di: Gao, Shenyuan, et al.
  Pubblicazione: (2025)
• Distilled Feature Fields Enable Few-Shot Language-Guided Manipulation
  di: Shen, William, et al.
  Pubblicazione: (2023)