Hongyin Zhang

Alibaba Group

収録論文 22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

• RynnValue: 時間的距離によるロボット価値基盤モデルのスケーリング
  価値基盤モデル2026/8/10

  ロボット操作のための価値基盤モデルRynnValueを提案。時間的距離を報酬ラベルとして用いることで、大規模な異種データから価値学習を可能にし、実世界の成功率を向上させた。

• RynnValue: Scaling Robotic Value Foundation Models with Temporal Distance
  2026/8/1
• World-Value-Action Model: Implicit Planning for Vision-Language-Action Systems
  2026/4/16
• World-Value-Action Model: Implicit Planning for Vision-Language-Action Systems
  2026/4/1
• MMaDA-VLA: Large Diffusion Vision-Language-Action Model with Unified Multi-Modal Instruction and Generation
  2026/3/1
• CRL-VLA: Continual Vision-Language-Action Learning
  2026/2/3
• CMR: Contractive Mapping Embeddings for Robust Humanoid Locomotion on Unstructured Terrains
  2026/2/1
• CRL-VLA: Continual Vision-Language-Action Learning
  2026/2/1
• RobustVLA: Robustness-Aware Reinforcement Post-Training for Vision-Language-Action Models
  2025/11/3
• RobustVLA: Robustness-Aware Reinforcement Post-Training for Vision-Language-Action Models
  2025/11/1
• VLA-RFT: Vision-Language-Action Reinforcement Fine-tuning with Verified Rewards in World Simulators
  2025/10/1
• Balancing Signal and Variance: Adaptive Offline RL Post-Training for VLA Flow Models
  2025/9/4
• Balancing Signal and Variance: Adaptive Offline RL Post-Training for VLA Flow Models
  2025/9/1
• Multi-Task Multi-Agent Reinforcement Learning via Skill Graphs
  2025/7/1
• ReinboT: Amplifying Robot Visual-Language Manipulation with Reinforcement Learning
  2025/5/1
• GEVRM: Goal-Expressive Video Generation Model For Robust Visual Manipulation
  2025/2/13
• GEVRM: Goal-Expressive Video Generation Model For Robust Visual Manipulation
  2025/2/1
• TDMPBC: Self-Imitative Reinforcement Learning for Humanoid Robot Control
  2025/2/1
• QUART-Online: Latency-Free Large Multimodal Language Model for Quadruped Robot Learning
  2024/12/1
• Unlock Reliable Skill Inference for Quadruped Adaptive Behavior by Skill Graph
  2023/11/1
• A Real-World Quadrupedal Locomotion Benchmark for Offline Reinforcement Learning
  2023/9/1
• Imitation and Adaptation Based on Consistency: A Quadruped Robot Imitates Animals from Videos Using Deep Reinforcement Learning
  2022/3/1