Kai Wang

Institute of Automation, Chinese Academy of Sciences

収録論文 23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

• HarnessWAM: 世界行動モデルにおける予測と熟考の橋渡し
  VLA/タスク計画2026/8/10

  世界行動モデル（WAM）の予測と実行のギャップを埋めるため、視覚言語モデルベースのタスクマネージャーとイベント駆動型の二重タイムスケールフィードバックループを備えたエージェントフレームワークを提案し、複雑なタスクの計画・実行・失敗回復を可能にした。

• 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。

• HarnessWAM: Bridging Prediction and Deliberation in World 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
• GigaWorld-Policy-0.5: A Faster and Stronger WAM Empowered by AutoResearch
  2026/7/1
• DIM-WAM: World-Action Modeling with Diverse Historical Event Memory
  2026/6/1
• WAM-Nav: Asymmetric Latent World-Action Modeling for Unified Visual Navigation
  2026/6/1
• LaWAM: Latent World Action Models for Efficient Dynamics-Aware Robot Policies
  2026/6/1
• Improving Vision-Language-Action Model Fine-Tuning with Structured Stage and Keyframe Supervision
  2026/6/1
• Adaptive Action Chunking at Inference-time for Vision-Language-Action Models
  2026/4/1
• 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
• EgoDemoGen: Egocentric Demonstration Generation for Viewpoint Generalization in Robotic Manipulation
  2025/9/1
• iLearnRobot: An Interactive Learning-Based Multi-Modal Robot with Continuous Improvement
  2025/7/1
• A Large Vision-Language Model based Environment Perception System for Visually Impaired People
  2025/4/1
• $\nu$-DBA: Neural Implicit Dense Bundle Adjustment Enables Image-Only Driving Scene Reconstruction
  2024/4/1
• Scenario Diffusion: Controllable Driving Scenario Generation With Diffusion
  2023/11/1
• NGEL-SLAM: Neural Implicit Representation-based Global Consistent Low-Latency SLAM System
  2023/11/1
• Implementation and Evaluation of Networked Model Predictive Control System on Universal Robot
  2023/7/1
• Deep Learning based Wearable Assistive System for Visually Impaired People
  2019/8/1
• Vision-based Robotic Grasping From Object Localization, Object Pose Estimation to Grasp Estimation for Parallel Grippers: A Review
  2019/5/1
• Deep Learning Based Robot for Automatically Picking up Garbage on the Grass
  2019/4/1