Cheng Chi
Renmin University of China
収録論文 49本 ・ フィジカルAI/ロボット学習
所属歴（論文より）: Renmin University of China（〜2026） ／ Beihang University（〜2026）
操作マニピュレーションVLA/世界モデル
※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。
- JEPA-WAM: Learning Vision-Language-Action Policies with Joint-Embedding World Modeling2026/8/1
- JEPA-WAM: Stage-Level Joint-Embedding Prediction for World-Action Models in Robot Manipulation2026/8/1
- VAMPO: Policy Optimization for Improving Visual Dynamics in Video Action Models2026/3/1
- SaPaVe: Towards Active Perception and Manipulation in Vision-Language-Action Models for Robotics2026/3/1
- PRM-as-a-Judge: A Dense Evaluation Paradigm for Fine-Grained Robotic Auditing2026/3/1
- Latent Reasoning VLA: Latent Thinking and Prediction for Vision-Language-Action Models2026/2/1
- Reshaping Action Error Distributions for Reliable Vision-Language-Action Models2026/2/1
- From Representational Complementarity to Dual Systems: Synergizing VLM and Vision-Only Backbones for End-to-End Driving2026/2/1
- Action-Sketcher: From Reasoning to Action via Visual Sketches for Long-Horizon Robotic Manipulation2026/1/1
- RoboBrain 2.5: Depth in Sight, Time in Mind2026/1/1
- RoboMirror: Understand Before You Imitate for Video to Humanoid Locomotion2025/12/1
- Embodied Robot Manipulation in the Era of Foundation Models: Planning and Learning Perspectives2025/12/1
- Towards Spatial Trace with Reasoning in Vision-Language Models for Robotics2025/12/1
- Robo-Dopamine: General Process Reward Modeling for High-Precision Robotic Manipulation2025/12/1
- Do You Have Freestyle? Expressive Humanoid Locomotion via Audio Control2025/12/1
- RoboCOIN: An Open-Sourced Bimanual Robotic Data Collection for Integrated Manipulation2025/11/1
- PIGEON: VLM-Driven Object Navigation via Points of Interest Selection2025/11/1
- Towards a Unified Understanding of Robot Manipulation: A Comprehensive Survey2025/10/1
- Robobench: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models as Embodied Brain2025/10/1
- TIGeR: Tool-Integrated Geometric Reasoning in Vision-Language Models for Robotics2025/10/1
- VCoT-Grasp: Grasp Foundation Models with Visual Chain-of-Thought Reasoning for Language-driven Grasp Generation2025/10/1
- RoboOS-NeXT: A Unified Memory-based Framework for Lifelong, Scalable, and Robust Multi-Robot Collaboration2025/10/1
- From Language to Locomotion: Retargeting-free Humanoid Control via Motion Latent Guidance2025/10/1
- RoboBrain 2.0 Technical Report2025/7/1
- RoboRefer: Towards Spatial Referring with Reasoning in Vision-Language Models for Robotics2025/6/1
- RoboOS: A Hierarchical Embodied Framework for Cross-Embodiment and Multi-Agent Collaboration2025/5/1
- Uni-Gaussians: Unifying Camera and Lidar Simulation with Gaussians for Dynamic Driving Scenarios2025/3/1
- Code-as-Monitor: Constraint-aware Visual Programming for Reactive and Proactive Robotic Failure Detection2024/12/1
- Adaptive Compliance Policy: Learning Approximate Compliance for Diffusion Guided Control2024/10/1
- RALTPER: A Risk-Aware Local Trajectory Planner for Complex Environment with Gaussian Uncertainty2024/8/1
- Flow as the Cross-Domain Manipulation Interface2024/7/1
- ManiWAV: Learning Robot Manipulation from In-the-Wild Audio-Visual Data2024/6/1
- DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset2024/3/1
- PaperBot: Learning to Design Real-World Tools Using Paper2024/3/1
- Universal Manipulation Interface: In-The-Wild Robot Teaching Without In-The-Wild Robots2024/2/1
- Open X-Embodiment: Robotic Learning Datasets and RT-X Models2023/10/1
- XSkill: Cross Embodiment Skill Discovery2023/7/1
- GICI-LIB: A GNSS/INS/Camera Integrated Navigation Library2023/6/1
- Diffusion Policy: Visuomotor Policy Learning via Action Diffusion2023/3/1
- RoboNinja: Learning an Adaptive Cutting Policy for Multi-Material Objects2023/2/1
- Robust Extrinsic Self-Calibration of Camera and Solid State LiDAR2023/2/1
- Cloth Funnels: Canonicalized-Alignment for Multi-Purpose Garment Manipulation2022/10/1
- DextAIRity: Deformable Manipulation Can be a Breeze2022/3/1
- Iterative Residual Policy: for Goal-Conditioned Dynamic Manipulation of Deformable Objects2022/3/1
- GarmentNets: Category-Level Pose Estimation for Garments via Canonical Space Shape Completion2021/4/1
- Occlusion-robust Deformable Object Tracking without Physics Simulation2021/1/1