Yan Wang

Tsinghua University

収録論文 54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

• StageWAM: ロボット操作におけるワールドアクションモデルのためのジョイント埋め込みステージ予測
  操作2026/8/11

  ロボット操作タスクにおいて、短期的な物理的未来に加えて、タスクの進行段階を表すセマンティックな未来を予測するStageWAMを提案し、成功率と実行効率を向上させた。

• JEPA-WAM: ロボット操作のためのワールドアクションモデルにおける段階レベル結合埋め込み予測
  マニピュレーション2026/8/11

  ロボット操作タスクにおいて、短期的な物理的未来と段階的な意味的未来を区別し、段階レベルの潜在目標を予測するJEPA-WAMを提案。50のタスクで成功率90.25%を達成し、実行ステップ数を削減した。

• JEPA-WAM: 共同埋め込み世界モデリングによる視覚・言語・行動ポリシーの学習
  VLA/世界モデル2026/8/10

  事前学習済みV-JEPA空間に基づく潜在世界モデルを導入し、遷移予測と行動生成を共有予測器で結合することで、ロボット制御の性能と汎化を向上させた。

• 4D-WAM: 軌跡フィールドによる世界行動モデルへの時空間認識の注入
  VLA2026/8/8

  ロボットの行動生成と動画予測を統合する世界行動モデルに、3次元軌跡フィールドの時空間知識を表現整合で注入する訓練戦略を提案。局所的な動き整合と長期的な目的地整合の2つの目的関数により、軌跡レベルの時空間表現を学習し、空間理解や実行精度、汎化性を向上させる。

• 4D-WAM: 軌跡フィールドによる世界行動モデルへの時空間認識の注入
  VLA2026/8/8

  ロボットの行動生成と動画予測を統合する世界行動モデルに、3次元軌跡フィールドの時空間知識を表現整合で注入する訓練戦略を提案し、空間理解と実行精度を向上させた。

• JEPA-WAM: Learning Vision-Language-Action Policies with Joint-Embedding World Modeling
  2026/8/1
• 4D-WAM: Infusing Spatiotemporal Awareness into World Action Models through Trajectory Fields
  2026/8/1
• JEPA-WAM: Stage-Level Joint-Embedding Prediction for World-Action Models in Robot Manipulation
  2026/8/1
• Adaptive-WAM: Quality-Guided Early-Exit Planning from Intermediate Video-Diffusion Features
  2026/8/1
• DINS-IO: Learned Inertial Odometry via Differentiable INS Consistency
  2026/7/1
• ST-WAM: Semantic-Temporal World Action Model for Robust Manipulation under Visual Distribution Shifts
  2026/7/1
• ASSCG: Just-Right Gating over Chattering for Fast-Slow LLM Planning in Autonomous Driving
  2026/6/1
• MV-Actor: Aligning Multi-View Semantics and Spatial Awareness for Bimanual Manipulation
  2026/6/1
• Planning-aligned Token Compression for Long-Context Autonomous Driving
  2026/6/1
• A Physics-Grounded Benchmark for Multi-Agent Dynamics in World Models
  2026/6/1
• Cosmos 3: Omnimodal World Models for Physical AI
  2026/6/1
• AR Forcing: Towards Long-Horizon Robot Navigation World Model
  2026/5/1
• CLOVER: Closed-Loop Value Estimation and Ranking for End-to-End Autonomous Driving Planning
  2026/5/1
• Reactive Planning based Control for Mobile Robots in Obstacle-Cluttered Environments
  2026/5/1
• RoboMemArena: A Comprehensive and Challenging Robotic Memory Benchmark
  2026/5/1
• CapVector: Learning Transferable Capability Vectors in Parametric Space for Vision-Language-Action Models
  2026/5/1
• Fast-dVLA: Accelerating Discrete Diffusion VLA to Real-Time Performance
  2026/3/1
• Devil is in Narrow Policy: Unleashing Exploration in Driving VLA Models
  2026/3/1
• DFM-VLA: Iterative Action Refinement for Robot Manipulation via Discrete Flow Matching
  2026/3/1
• Accelerating Structured Chain-of-Thought in Autonomous Vehicles
  2026/2/1
• From Representational Complementarity to Dual Systems: Synergizing VLM and Vision-Only Backbones for End-to-End Driving
  2026/2/1
• FRAPPE: Infusing World Modeling into Generalist Policies via Multiple Future Representation Alignment
  2026/2/1
• Counterfactual VLA: Self-Reflective Vision-Language-Action Model with Adaptive Reasoning
  2025/12/1
• Latent Chain-of-Thought World Modeling for End-to-End Driving
  2025/12/1
• Alpamayo-R1: Bridging Reasoning and Action Prediction for Generalizable Autonomous Driving in the Long Tail
  2025/11/1
• MoE-Based Learned Inertial Odometry for Bicycle Localization
  2025/10/1
• Efficient Multi-Camera Tokenization with Triplanes for End-to-End Driving
  2025/6/1
• SELC: Self-Supervised Efficient Local Correspondence Learning for Low Quality Images
  2025/4/1
• Low-Complexity Cooperative Payload Transportation for Nonholonomic Mobile Robots Under Scalable Constraints
  2025/2/1
• IROAM: Improving Roadside Monocular 3D Object Detection Learning from Autonomous Vehicle Data Domain
  2025/1/1
• Extrapolated Urban View Synthesis Benchmark
  2024/12/1
• MR-ULINS: A Tightly-Coupled UWB-LiDAR-Inertial Estimator with Multi-Epoch Outlier Rejection
  2024/8/1
• Revisiting Sparse Rewards for Goal-Reaching Reinforcement Learning
  2024/7/1
• Asynchronous Large Language Model Enhanced Planner for Autonomous Driving
  2024/6/1
• A New Method in Facial Registration in Clinics Based on Structure Light Images
  2024/5/1
• SceneVerse: Scaling 3D Vision-Language Learning for Grounded Scene Understanding
  2024/1/1
• Ordering-Flexible Multi-Robot Coordination for MovingTarget Convoying Using Long-TermTask Execution
  2024/1/1
• Interpretable Reinforcement Learning for Robotics and Continuous Control
  2023/11/1
• Waymax: An Accelerated, Data-Driven Simulator for Large-Scale Autonomous Driving Research
  2023/10/1
• Predictive Control for Autonomous Driving with Uncertain, Multi-modal Predictions
  2023/10/1
• DynaVIG: Monocular Vision/INS/GNSS Integrated Navigation and Object Tracking for AGV in Dynamic Scenes
  2022/11/1
• Real-Time Reinforcement Learning for Vision-Based Robotics Utilizing Local and Remote Computers
  2022/10/1
• Vehicle Trajectory Tracking Through Magnetic Sensors: A Case Study of Two-lane Road
  2022/9/1
• Robotic Imitation of Human Assembly Skills Using Hybrid Trajectory and Force Learning
  2021/3/1
• A Reliable Gravity Compensation Control Strategy for dVRK Robotic Arms With Nonlinear Disturbance Forces
  2020/1/1
• LDLS: 3-D Object Segmentation Through Label Diffusion From 2-D Images
  2019/10/1
• Motion Planning through Demonstration to Deal with Complex Motions in Assembly Process
  2019/10/1
• A Convex Optimization-based Dynamic Model Identification Package for the da Vinci Research Kit
  2019/2/1
• Model-Driven Feed-Forward Prediction for Manipulation of Deformable Objects
  2016/7/1