Zhi Hou

収録論文 9本 ・ フィジカルAI/ロボット学習

※arXiv著者名で収集。同姓同名の別人の論文が含まれる場合があります。

論文

• ExToken: Structured Exploration for Efficient Vision-Language-Action Reinforcement Fine-tuning
  2026/7/1
• ACE-Brain-0.5: A Unified Embodied Foundational Model for Physical Agentic AI
  2026/7/1
• ACE-Brain-0: Spatial Intelligence as a Shared Scaffold for Universal Embodiments
  2026/3/1
• Grounding Actions in Camera Space: Observation-Centric Vision-Language-Action Policy
  2025/8/1
• Visual Embodied Brain: Let Multimodal Large Language Models See, Think, and Control in Spaces
  2025/6/1
• Dita: Scaling Diffusion Transformer for Generalist Vision-Language-Action Policy
  2025/3/1
• Diffusion Transformer Policy
  2024/10/1
• Discovering Human-Object Interaction Concepts via Self-Compositional Learning
  2022/3/1
• Affordance Transfer Learning for Human-Object Interaction Detection
  2021/4/1