Yuxuan Kuang

I am a Ph.D. student in the CMU Robotics Institute, working with Prof. Shubham Tulsiani and Prof. Katerina Fragkiadaki. I'm also a research intern at NVIDIA DAIR. I received my Bachelor's degree in Computer Science from Peking University. During my undergrad years, I have been fortunate to work with Prof. Yue Wang, Prof. Marco Pavone, Prof. Meng Jiang, and Prof. He Wang.

I study Robotics, Reinforcement Learning, and 3D/4D Vision. I work on general-purpose dexterous manipulation, from a real-to-sim-to-real and agentic perspective. My research objective is to endow Embodied AI Agents working in complex, unstructured real-world scenes with generalizability, dexterity, and adaptability.

How to pronounce my first name?

To approximate: replace the letter "x" with "sh". I also go by Gavin.
Here is a standard Chinese pronunciation of my first name if you wonder:

Email / GitHub / Google Scholar / Twitter

Click for domain randomization

Research

*: Equal Contributions; †: Equal Advising; ‡: Project Lead

	Learning Adaptable Dexterous Skills via Hybrid Dexterous Mimicking Yuxuan Kuang, Jiashun Wang^‡, Yixuan Sun, Yufei Ye, Sungjae Park, Umar Iqbal, Katerina Fragkiadaki^†, Shubham Tulsiani^† Paper / Project / Code arXiv preprint, 2026.
	Dex4D: Task-Agnostic Point Track Policy for Zero-Shot Dexterous Manipulation Yuxuan Kuang, Sungjae Park, Katerina Fragkiadaki^†, Shubham Tulsiani^† Paper / Project / Code Conference on Robot Learning (CoRL), 2026.
	SkillBlender: Towards Versatile Humanoid Whole-Body Loco-Manipulation via Skill Blending Yuxuan Kuang, Haoran Geng, Amine Elhafsi, Tan-Dzung Do, Pieter Abbeel, Jitendra Malik, Marco Pavone, Yue Wang Paper / Project / Code arXiv preprint, 2025.
	RoboVerse: Towards a Unified Platform, Dataset and Benchmark for Scalable and Generalizable Robot Learning RoboVerse Team Paper / Project / Code Robotics: Science and Systems (RSS), 2025. (Oral Presentation)
	FetchBot: Learning Generalizable Object Fetching in Cluttered Scenes via Zero-Shot Sim2Real Weiheng Liu, Yuxuan Wan, Jilong Wang, Yuxuan Kuang, Wenbo Cui, Xuesong Shi, Haoran Li, Dongbin Zhao, Zhizheng Zhang^†, He Wang^† Paper / Project / Code Conference on Robot Learning (CoRL), 2025. (Oral Presentation)
	A₀: An Affordance-Aware Hierarchical Model for General Robotic Manipulation Rongtao Xu, Jian Zhang, Minghao Guo, Youpeng Wen, Haoting Yang, Min Lin, Jianzheng Huang, Zhe Li, Kaidong Zhang, Liqiong Wang, Yuxuan Kuang, Meng Cao, Feng Zheng^†, Xiaodan Liang^† Paper / Project / Code International Conference on Computer Vision (ICCV), 2025.
	RAM: Retrieval-Based Affordance Transfer for Generalizable Zero-Shot Robotic Manipulation Yuxuan Kuang, Junjie Ye, Haoran Geng, Jiageng Mao, Congyue Deng, Leonidas Guibas, He Wang, Yue Wang Paper / Project / Code Conference on Robot Learning (CoRL), 2024.* (Oral Presentation, 4.5% acceptance rate)
	OpenFMNav: Towards Open-Set Zero-Shot Object Navigation via Vision-Language Foundation Models Yuxuan Kuang, Hai Lin, Meng Jiang Paper / Project / Code Findings of Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL), 2024.
	STOPNet: Multiview-based 6-DoF Suction Detection for Transparent Objects on Production Lines Yuxuan Kuang, Qin Han, Danshi Li, Qiyu Dai, Lian Ding, Dong Sun, Hanlin Zhao, He Wang^† Paper / Project / Code International Conference on Robotics and Automation (ICRA), 2024. (Oral Presentation)