Jing Liu

Institute of Automation, Chinese Academy of Sciences

収録論文 26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

• AtlasVLA: 視覚言語行動モデルのための持続的な世界・自我状態モデリング
  VLA2026/8/7

  単眼カメラのみで長期的なタスクを遂行できるよう、視覚言語行動モデルに持続的な世界状態メモリと自我作業メモリを導入し、空間的推論を強化したフレームワークを提案した。

• XEWorld：行動条件付きワールドモデルは未知のロボット形態に汎化できるか？
  ワールドモデル2026/8/6

  ロボット操作のための行動条件付きワールドモデルが、未見のロボット形態に対して物理ダイナミクスを正しく予測できるかを検証するため、クロスエンボディメントテストベッドXEWorldを導入し、既存モデルの限界を分析した。

• AtlasVLA: Persistent World-Ego State Modeling for Vision-Language-Action Models
  2026/8/1
• XEWorld: Can Action-Conditioned World Models Generalize to Unseen Robot Embodiments?
  2026/8/1
• FlowWAM: Optical Flow as a Unified Action Representation for World Action Models
  2026/7/1
• ReCoVLA: VLM-Guided Reward Compilation for Failure Recovery in Vision-Language-Action Policies
  2026/6/8
• ReCoVLA: VLM-Guided Reward Compilation for Failure Recovery in Vision-Language-Action Policies
  2026/6/1
• SKIP: Sparse Keyframe Interpolation Paradigm for Efficient Embodied World Models
  2026/6/1
• NavWM: A Unified Navigation World Model for Foresight-Driven Planning
  2026/6/1
• WAM-Nav: Asymmetric Latent World-Action Modeling for Unified Visual Navigation
  2026/6/1
• VeriSpace: Spatially Grounded Action Verification for Vision-Language-Action Models
  2026/6/1
• E-TTS: A New Embodied Test-Time Scaling Framework for Robotic Manipulation
  2026/6/1
• SurveilNav: Collaborative Object Goal Navigation with Robot and Surveillance System
  2026/6/1
• SpatialVAM:Spatial-Aware Multi-View Video Diffusion as a Data-Efficient Robot Policy
  2026/4/1
• FloorPlan-VLN: A New Paradigm for Floor Plan Guided Vision-Language Navigation
  2026/3/1
• Embedding Morphology into Transformers for Cross-Robot Policy Learning
  2026/3/1
• BridgeV2W: Bridging Video Generation Models to Embodied World Models via Embodiment Masks
  2026/2/1
• UAOR: Uncertainty-aware Observation Reinjection for Vision-Language-Action Models
  2026/2/1
• Untethered thin dielectric elastomer actuated soft robot
  2025/12/1
• UrbanNav: Learning Language-Guided Urban Navigation from Web-Scale Human Trajectories
  2025/12/1
• PIGEON: VLM-Driven Object Navigation via Points of Interest Selection
  2025/11/1
• C-NAV: Towards Self-Evolving Continual Object Navigation in Open World
  2025/10/1
• EgoDemoGen: Egocentric Demonstration Generation for Viewpoint Generalization in Robotic Manipulation
  2025/9/1
• COSMO: Combination of Selective Memorization for Low-cost Vision-and-Language Navigation
  2025/3/1
• FlexVLN: Flexible Adaptation for Diverse Vision-and-Language Navigation Tasks
  2025/3/1
• Planning-Assisted Context-Sensitive Autonomous Shepherding of Dispersed Robotic Swarms in Obstacle-Cluttered Environments
  2023/1/1