👋 I’m currently a Phd Candidate of Hong Kong University of Science and Technology(HKUST), supervised by Prof. Ping Tan

🤔 My research interests include Embodied AI and Generative AI.

🙋‍♂️ If you are seeking any form of academic cooperation, please feel free to email me at hyubq@connect.ust.hk.

🎓 I graduated from Nanjing University with a B.S. degree in Electronic Science and Engineering. I had an internship at the CITE LAB, Nanjing University, supervised by Prof. Xun Cao and Prof. Shen Qiu

Industry Experience

Tencent Robotics X, Shenzhen, China 2025.08 - Present

• Project: VLA/WAM Pretraining for Robot Manipulation
• Worked with Dr. Haitao Lin

News

• 2026.06:   🎉 Our paper is accepted by RSS 2026!
• 2024.06:   🎉 I was awarded as Outstanding Graduate of Nanjing Universtiy.
• 2024.04:   🎉 HKPFS get!
• 2023.12:   🎉 We won the Gold prize in National College Students Innovation and Entrepreneurship Competition!
• 2023.9:   🎉 Our paper is accepted by ACM MM!
• 2022.8:   🎉 We won the First prize of National College students Electronic Design Competition!

Publications

Under Review

GeniWorld: A Generalizable Interactive World Model for Robotic Manipulation via Visual Actions

Chenghao Gu*, Hanyang Yu*, Jingbo Zhang, Haitao Lin, Wenyao Zhang, Jinghe Wang, Hanglei Jin, Shuzhao Xie, Jingyan Jiang, Zhi Wang

- GeniWorld converts robot actions into visual actions for controllable world modeling, enabling closed-loop interaction, robust generalization to unseen environments, and improved downstream policies.

RSS 2026 · Oral Presentation

PoseVLA: Universal Pose Pretraining for Generalizable Vision-Language-Action Policies

Haitao Lin*, Hanyang Yu*, Jingshun Huang*, He Zhang, Yonggen Ling, Ping Tan, Xiangyang Xue, Yanwei Fu

- PoseVLA decouples VLA training into universal pose pretraining and embodiment-specific post-training, learning transferable 3D spatial priors for efficient robot policy adaptation.

Under Review

MatchingPolicy: Correspondence-Aware Policy Enables Cross-Object In-Context Learning

Qijin She*, Hanyang Yu*, Zeming Li, Ping Tan

- MatchingPolicy decouples demonstration-to-scene matching from policy learning and conditions actions on dense semantic correspondences, enabling robust few-shot generalization across unseen objects and novel manipulation scenarios.

Arxiv 2024

LM-Gaussian: Boost Sparse-view 3D Gaussian Splatting with Large Model Priors

Hanyang Yu, Xiaoxiao Long†, Ping Tan

- We aim to address sparse-view reconstruction of a 3D scene by leveraging priors from large-scale vision models.

ACM MM 2023

WormTrack: Dataset and Benchmark for Multi-Object Tracking in Worm Crowds

Zhiyu Jin, Hanyang Yu, Chen Haul, Linxiang Wang, Qiu Shen, Xun Cao,

- We studies on the challenges and existing solutions for MOT in worm crowds by building a well-designed dataset!

Selected Honors and Awards

• Outstanding Graduate of Nanjing University, 2024
• National Gold Award, China International College Students’ Innovation Competition, 2023
• Provincial First Prize, National College Students Electronic Design Competition, 2022
• Huawei Cup Gold Award (Top One), 2023
• People’s Scholarship · Jin Xiao Electronics Scholarship · People’s Special Talent Scholarship

Educations

• 2024.08 - (now), PhD, ECE, The Hong Kong University of Science and Technology (HKUST), HongKong.
• 2020.09 - 2024.06, Undergraduate, School of Electronics Science and Engineering, Nanjing University.
• 2017.09 - 2020.06, Jiangsu Tianyi High School, WUXI.