Liang Wang

Institute of Automation, Chinese Academy of Sciences

収録論文 33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

• 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。

• BridgeVLA++: データ効率的で汎化性が高く、メモリ拡張された3D操作のための視覚-言語-行動フレームワーク
  VLA/操作2026/8/5

  事前学習済み視覚言語モデルを活用した3Dロボット操作フレームワークBridgeVLAを拡張し、空間的・時間的メモリを統合することで、データ効率と汎化性を保ちつつ、記憶依存の操作タスクで最先端の性能を達成した。

• SyncPlan: Long-Horizon LLM Coordination with Explicit Synchronization and Adaptive Correction
  2026/8/1
• BridgeVLA++: A Data-Efficient, Generalizable, and Memory-Augmented Vision-Language-Action Framework for 3D Manipulation
  2026/8/1
• XEWorld: Can Action-Conditioned World Models Generalize to Unseen Robot Embodiments?
  2026/8/1
• Stop to Decide: Latency-Aware Proprioceptive Navigation Primitives for Mapping-Free Quadruped Inspection
  2026/7/1
• FlowWAM: Optical Flow as a Unified Action Representation for World Action Models
  2026/7/1
• E-TTS: A New Embodied Test-Time Scaling Framework for Robotic Manipulation
  2026/6/1
• DIM-WAM: World-Action Modeling with Diverse Historical Event Memory
  2026/6/1
• Improving Vision-Language-Action Model Fine-Tuning with Structured Stage and Keyframe Supervision
  2026/6/1
• GUIDE: Goal-Initialized Directional Understanding for End-to-End Visual Navigation
  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
• UAOR: Uncertainty-aware Observation Reinjection for Vision-Language-Action Models
  2026/2/1
• BridgeV2W: Bridging Video Generation Models to Embodied World Models via Embodiment Masks
  2026/2/1
• PUMA: Perception-driven Unified Foothold Prior for Mobility Augmented Quadruped Parkour
  2026/1/1
• Embodied Co-Design for Rapidly Evolving Agents: Taxonomy, Frontiers, and Challenges
  2025/12/1
• RflyUT-Sim: A Simulation Platform for Development and Testing of Complex Low-Altitude Traffic Control
  2025/12/1
• VERM: Leveraging Foundation Models to Create a Virtual Eye for Efficient 3D Robotic Manipulation
  2025/12/1
• SimScale: Learning to Drive via Real-World Simulation at Scale
  2025/11/1
• ZJUNlict Extended Team Description Paper 2025
  2025/11/1
• EgoDemoGen: Egocentric Demonstration Generation for Viewpoint Generalization in Robotic Manipulation
  2025/9/1
• EC-Flow: Enabling Versatile Robotic Manipulation from Action-Unlabeled Videos via Embodiment-Centric Flow
  2025/7/1
• BridgeVLA: Input-Output Alignment for Efficient 3D Manipulation Learning with Vision-Language Models
  2025/6/1
• Orchestrating Joint Offloading and Scheduling for Low-Latency Edge SLAM
  2025/2/1
• MCRL4OR: Multimodal Contrastive Representation Learning for Off-Road Environmental Perception
  2025/1/1
• Constraint-Aware Zero-Shot Vision-Language Navigation in Continuous Environments
  2024/12/1
• TopoSD: Topology-Enhanced Lane Segment Perception with SDMap Prior
  2024/11/1
• GR-MG: Leveraging Partially Annotated Data via Multi-Modal Goal-Conditioned Policy
  2024/8/1
• Pose-Graph Attentional Graph Neural Network for Lidar Place Recognition
  2023/9/1
• ETPNav: Evolving Topological Planning for Vision-Language Navigation in Continuous Environments
  2023/4/1
• BEVBert: Multimodal Map Pre-training for Language-guided Navigation
  2022/12/1
• 1st Place Solutions for RxR-Habitat Vision-and-Language Navigation Competition (CVPR 2022)
  2022/6/1