VLM Agents Generate Their Own Memories: Distilling Experience into Embodied Programs of Thought

Documenti analoghi

• HELPER-X: A Unified Instructable Embodied Agent to Tackle Four Interactive Vision-Language Domains with Memory-Augmented Language Models
  di: Sarch, Gabriel, et al.
  Pubblicazione: (2024)
• Grounded Reinforcement Learning for Visual Reasoning
  di: Sarch, Gabriel, et al.
  Pubblicazione: (2025)
• ODIN: A Single Model for 2D and 3D Segmentation
  di: Jain, Ayush, et al.
  Pubblicazione: (2024)
• DreamScene4D: Dynamic Multi-Object Scene Generation from Monocular Videos
  di: Chu, Wen-Hsuan, et al.
  Pubblicazione: (2024)
• Reanimating Images using Neural Representations of Dynamic Stimuli
  di: Yeung, Jacob, et al.
  Pubblicazione: (2024)