Scholar
Haoqi Yuan
Google Scholar ID: QD_ynSgAAAAJ
Peking University
Machine Learning
Reinforcement Learning
Embodied AI
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
331
H-index
7
i10-index
7
Publications
17
Co-authors
9
list available
Contact
Email
yhq@pku.edu.cn
CV
Open ↗
GitHub
Open ↗
Publications
14 items
Conservative Offline Robot Policy Learning via Posterior-Transition Reweighting
2026
Cited
0
Joint-Aligned Latent Action: Towards Scalable VLA Pretraining in the Wild
2026
Cited
0
Rethinking Visual-Language-Action Model Scaling: Alignment, Mixture, and Regularization
2026
Cited
0
Being-H0.5: Scaling Human-Centric Robot Learning for Cross-Embodiment Generalization
2026
Cited
4
UniTacHand: Unified Spatio-Tactile Representation for Human to Robotic Hand Skill Transfer
2025
Cited
0
Universal Dexterous Functional Grasping via Demonstration-Editing Reinforcement Learning
2025
Cited
0
Spatial-Aware VLA Pretraining through Visual-Physical Alignment from Human Videos
2025
Cited
0
DiG-Flow: Discrepancy-Guided Flow Matching for Robust VLA Models
2025
Cited
0
Load more
Resume (English only)
Academic Achievements
- Published Papers:
- DemoGrasp: Universal Dexterous Grasping from a Single Demonstration
- Being-0: A Humanoid Robotic Agent with Vision-Language Models and Modular Skills
- Cross-Embodiment Dexterous Grasping with Reinforcement Learning
- Efficient Residual Learning with Mixture-of-Experts for Universal Dexterous Grasping
- Pre-Trained Multi-Goal Transformers with Prompt Optimization for Efficient Online Adaptation
Research Experience
- Position: Fifth-year Ph.D. student at Peking University
- Research Projects: Dexterous grasping, humanoid robotic control, etc.
Education
- Degree: Ph.D. student
- University: Peking University
- Advisor: Prof. Zongqing Lu
- Time: 2021 to present
- Bachelor's degree: Turing Class, Peking University
Background
- Research Interests: reinforcement learning (RL) and embodied AI
- Current Focus: Scalable learning methods for dexterous hands and humanoid robots manipulation; Efficient RL for open-world, embodied agents
Miscellany
Personal interests and other information not provided
Co-authors
9 total
Zongqing Lu
Peking University | BeingBeyond
Hao Dong
Tenured Associate Professor at Peking University
Shaoteng Liu
Adobe Research, CUHK
Börje F. Karlsson
Beijing Academy of Artificial Intelligence (BAAI)
Zihan Ding
Princeton University
Co-author 6
Yihao Zhao
Peking University
Baoquan Chen
Peking University, IEEE Fellow
×
Welcome back
Sign in to Agora
Welcome back! Please sign in to continue.
Email address
Password
Forgot password?
Continue
Do not have an account?
Sign up