Hi! I am Tianxing Chen (Chinese name: 陈天行), a first-year Ph.D. student at MMLab@HKU (since Sep. 2025), supervised by Prof. Ping Luo and working closely with Dr. Yao Mu. My research focuses on Embodied AI, including robotic foundation models, generalizable manipulation policies (e.g., VLA, diffusion policy), and robot data synthesizers.

I have published multiple papers at top venues such as CVPR, RSS, and ACL. My work received the Best Paper Award at the ECCV 2024 MAAS Workshop, an Outstanding Poster Award at ChinaSI, and a CVPR Highlight recognition. Beyond research, I have been honored with the CCF Elite Collegiate Award (99 nationwide) and the “Excellent Star of SZU”, the highest undergraduate honor at Shenzhen University (ranked 2/30,000). I also won a silver medal in the ACM-ICPC regional competition and was national runner-up in the RAICOM robotics developer competition.

I am the co-founder of Lumina Embodied AI Community, and have served as an organizer of the CVPR 2025 MEIS Workshop, the CVPR 2025 RoboTwin Dual-Arm Collaboration Challenge, and the Greater Bay Area Embodied AI Workshop. I am also a student committee member of the Autonomous Robotic Technology Seminar (ARTS). In addition, I share my thoughts on research and technology as a blogger and vlogger, with over 14k followers on Rednote 🎒@TianxingChen (陈天行).

Feel free to contact me by email if you are interested in discussing or collaborating with me.

See My Google Scholar Profile or My Homepage for more details.

• [arXiv 25] RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulation, Webpage / Repo
• [Technical Report] Benchmarking Generalizable Bimanual Manipulation: RoboTwin Dual-Arm Collaboration Challenge at CVPR 2025 MEIS Workshop, Webpage
• [CVPR 25 (Highlight)] RoboTwin: Dual-Arm Robot Benchmark with Generative Digital Twins, Webpage / Repo
• [CVPR 25] G3Flow: Generative 3D Semantic Flow for Pose-aware and Generalizable Object Manipulation, Webpage, Repo
• [ACL 25] Text2World: Benchmarking Large Language Models for Symbolic World Model Generation, Webpage, Repo
• [arXiv 24] Articulated Object Manipulation using Online Axis Estimation with SAM2-Based Tracking, Webpage / Repo
• [ECCV 24 Workshop (Best Paper)] RoboTwin: Dual-Arm Robot Benchmark with Generative Digital Twins (early version), Webpage / Repo

• [arXiv 25] HyCodePolicy: Hybrid Language Controllers for Multimodal Monitoring and Decision in Embodied Agents, arXiv
• [arXiv 25] AutoBio: A Simulation and Benchmark for Robotic Automation in Digital Biology Laboratory, Repo
• [arXiv 25] AVR: Active Vision-Driven Robotic Precision Manipulation with Viewpoint and Focal Length Optimization
• [RSS 25] CordViP: Correspondence-based Visuomotor Policy for Dexterous Manipulation in Real-World, Webpage
• [CVPR 25] DexHandDiff: Interaction-aware Diffusion Planning for Adaptive Dexterous Manipulation, Webpage
• [ACL 25] HiAgent: Hierarchical Working Memory Management for Solving Long-Horizon Agent Tasks with Large Language Model, arXiv
• [arXiv 24] ManiCM: Real-time 3D Diffusion Policy via Consistency Model for Robotic Manipulation: Webpage / Repo
• [ICARM 24] Robust UAV Policy Learning for Urban Infrastructure Surface Screening, Paper

• Embodied-AI-Guide 具身智能技术指南: Repo
• Awesome-Embodied-AI-Job 具身智能招贤榜: Repo