Yinchuan Li

収録論文 14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

• AffordanceVLA: A Vision-Language-Action Model Empowering Action Generation through Affordance-Aware Understanding
  2026/6/1
• Affordance Agent Harness: Verification-Gated Skill Orchestration
  2026/5/1
• Panoramic Affordance Prediction
  2026/3/1
• ActionCodec: What Makes for Good Action Tokenizers
  2026/2/1
• PhysToolBench: Benchmarking Physical Tool Understanding for MLLMs
  2025/10/1
• Two-Steps Diffusion Policy for Robotic Manipulation via Genetic Denoising
  2025/10/1
• STAR: Learning Diverse Robot Skill Abstractions through Rotation-Augmented Vector Quantization
  2025/6/1
• DeCo: Task Decomposition and Skill Composition for Zero-Shot Generalization in Long-Horizon 3D Manipulation
  2025/5/1
• Conditioning Matters: Training Diffusion Policies is Faster Than You Think
  2025/5/1
• EmbodiedMAE: A Unified 3D Multi-Modal Representation for Robot Manipulation
  2025/5/1
• Few-Shot Vision-Language Action-Incremental Policy Learning
  2025/4/1
• RA-DP: Rapid Adaptive Diffusion Policy for Training-Free High-frequency Robotics Replanning
  2025/3/1
• Spatial-Temporal Graph Diffusion Policy with Kinematic Modeling for Bimanual Robotic Manipulation
  2025/3/1
• 3D-AffordanceLLM: Harnessing Large Language Models for Open-Vocabulary Affordance Detection in 3D Worlds
  2025/2/1