Jianfei Yang

Nanyang Technological University

収録論文 50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

• 統一条件・行動モデリングによる高精度ワンステップ行動生成
  マニピュレーション2026/8/17

  条件と行動を共有トークン空間で統一的にモデリングするUCA-Flowを提案し、推論速度を大幅に向上させつつ成功率を9.3ポイント改善した。

• 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。

• ω-0: 人間型ロボットの同時移動操作のための潜在予測世界行動モデル
  全身制御2026/8/6

  人間型ロボットが移動と操作を同時に行うための、言語指示と視覚・状態情報から全身の行動潜在変数を直接予測する世界行動モデルを提案し、実世界の家事タスクで有効性を示した。

• $\omega$-0: A Latent Predictive World Action Model for Concurrent Humanoid Loco-Manipulation
  2026/8/1
• RynnValue: Scaling Robotic Value Foundation Models with Temporal Distance
  2026/8/1
• Learning Physical Interaction: A Survey of Tactile- and Force-aware Robot Learning
  2026/8/1
• RynnBrain 1.1: Towards More Capable and Generalizable Embodied Foundation Model
  2026/7/1
• Data Pyramid for Embodied Manipulation: A Survey
  2026/7/1
• AXIS: A Growable Community-Driven Data Engine for Scalable Robot Manipulation
  2026/7/1
• FORGE: Towards Functional Tool-Use Generalization via Keypoint Trajectory Reasoning
  2026/7/1
• EM-Fall: Embodied mmWave Sensing for Day-and-Night Fall Detection on Humanoid Robots
  2026/6/1
• ActiveVital: Geometry-Aware Embodied Vital Signs Monitoring for Home Healthcare Robots
  2026/6/1
• Rethinking Implicit Spatial Representation in Visuomotor Policy Learning
  2026/6/1
• APEX: Adaptive Policy Execution for Precise Manipulation
  2026/6/1
• ADAPT: Analytical Disturbance-Aware Policy Training for Humanoid Locomotion
  2026/6/1
• GIVE: Grounding Human Gestures in Vision-Language-Action Models
  2026/6/1
• AerialClaw: An Open-Source Framework for LLM-Driven Autonomous Aerial Agents
  2026/6/1
• World Model for Robot Learning: A Comprehensive Survey
  2026/5/1
• MARS Policy: Multimodality Only When It Matters
  2026/5/1
• Gaze2Act: Gaze-Conditioned Vision-Language-Action Policies for Interactive Robot Manipulation
  2026/5/1
• FLASH: Efficient Visuomotor Policy via Sparse Sampling
  2026/5/1
• Feedback World Model Enables Precise Guidance of Diffusion Policy
  2026/5/1
• CompassAD: Intent-Driven 3D Affordance Grounding in Functionally Competing Objects
  2026/4/1
• RoboForge: Physically Optimized Text-guided Whole-Body Locomotion for Humanoids
  2026/3/1
• OmniVLN: Omnidirectional 3D Perception and Token-Efficient LLM Reasoning for Visual-Language Navigation across Air and Ground Platforms
  2026/3/1
• RoCo Challenge at AAAI 2026: Benchmarking Robotic Collaborative Manipulation for Assembly Towards Industrial Automation
  2026/3/1
• Chameleon: Control-Indexed Prospective Memory for Visuomotor Manipulation
  2026/3/1
• Trace-Focused Diffusion Policy for Multi-Modal Action Disambiguation in Long-Horizon Robotic Manipulation
  2026/2/1
• Action-to-Action Flow Matching
  2026/2/1
• RynnBrain: Open Embodied Foundation Models
  2026/2/1
• WaveMan: mmWave-Based Room-Scale Human Interaction Perception for Humanoid Robots
  2026/1/1
• RF-MatID: Dataset and Benchmark for Radio Frequency Material Identification
  2026/1/1
• $\mathbf{M^3A}$ Policy: Mutable Material Manipulation Augmentation Policy through Photometric Re-rendering
  2025/12/1
• When Robots Should Say "I Don't Know": Benchmarking Abstention in Embodied Question Answering
  2025/12/1
• From Human Intention to Action Prediction: Intention-Driven End-to-End Autonomous Driving
  2025/12/1
• DIPOLE: Fusing Vision and Geometry for Robust Visuomotor Generalization
  2025/11/1
• Mask2IV: Interaction-Centric Video Generation via Mask Trajectories
  2025/10/1
• RM-RL: Role-Model Reinforcement Learning for Precise Robot Manipulation
  2025/10/1
• REI-Bench: Can Embodied Agents Understand Vague Human Instructions in Task Planning?
  2025/5/1
• QLIO: Quantized LiDAR-Inertial Odometry
  2025/3/1
• Audio Array-Based 3D UAV Trajectory Estimation with LiDAR Pseudo-Labeling
  2024/12/1
• Unsupervised UAV 3D Trajectories Estimation with Sparse Point Clouds
  2024/12/1
• NoisyEQA: Benchmarking Embodied Question Answering Against Noisy Queries
  2024/12/1
• AV-PedAware: Self-Supervised Audio-Visual Fusion for Dynamic Pedestrian Awareness
  2024/11/1
• AIR-Embodied: An Efficient Active 3DGS-based Interaction and Reconstruction Framework with Embodied Large Language Model
  2024/9/1
• Salient Sparse Visual Odometry With Pose-Only Supervision
  2024/4/1
• Compact 3D Gaussian Splatting For Dense Visual SLAM
  2024/3/1
• MMAUD: A Comprehensive Multi-Modal Anti-UAV Dataset for Modern Miniature Drone Threats
  2024/2/1
• MoPA: Multi-Modal Prior Aided Domain Adaptation for 3D Semantic Segmentation
  2023/9/1
• Multi-Modal Continual Test-Time Adaptation for 3D Semantic Segmentation
  2023/3/1