Mingyu Liu

Zhejiang University

収録論文 12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

• AdvDex: 関節整合アクションと敵対的学習による人間のデモからの巧みな操作学習
  巧みな操作/VLA/身体間転移2026/8/14

  人間とロボットのデモを統合したVLAフレームワークを提案し、関節整合アクション空間と敵対的学習により異なる身体間の汎化を実現した。

• Perfect Demo Makes Poor Teacher: Learning Robust Alignment from Critical Motion Segments
  2026/6/1
• What to Ignore, What to React: Visually Robust RL Fine-Tuning of VLA Models
  2026/5/1
• World Guidance: World Modeling in Condition Space for Action Generation
  2026/2/1
• NoTVLA: Semantics-Preserving Robot Adaptation via Narrative Action Interfaces
  2025/10/1
• GAE: Unleashing Physical Potential of VLM with Generalizable Action Expert
  2025/10/1
• StaMo: Unsupervised Learning of Generalizable Robot Motion from Compact State Representation
  2025/10/1
• Learning Primitive Embodied World Models: Towards Scalable Robotic Learning
  2025/8/1
• ODYSSEY: Open-World Quadrupeds Exploration and Manipulation for Long-Horizon Tasks
  2025/8/1
• Affordance-R1: Reinforcement Learning for Generalizable Affordance Reasoning in Multimodal Large Language Model
  2025/8/1
• VQ-VLA: Improving Vision-Language-Action Models via Scaling Vector-Quantized Action Tokenizers
  2025/7/1
• CoMo: Learning Continuous Latent Motion from Internet Videos for Scalable Robot Learning
  2025/5/1