Welcome to my homepage! I am Providence / 洪少观:

I am a first-year Integrated M.Phil - Ph.D Candidate at the School of AI & DS, University of Science and Technology of China (USTC), advised by Prof. Jingrun Chen, and I also collaborate with associate researcher Congcong Zhu. If everything goes well, I will transfer to the City University of Hong Kong (CityUHK) Joint Ph.D Degree Program in Fall 2027, co-advised by Prof. Gerhard Petrus Hancke and Prof. Rynson W. H. Lau at Department of Computer Science. I received my B.Eng degree with Honors in Computer Science from Yuan Longping Class at Southwest University (SWU) in 2025.

I previously held internship positions as Researcher @ miHoYo / HoYoverse, Student Researcher @ Ubisoft La Forge, and Assistant Research Algorithm Engineer @ iFLYTEK Research. I have published 2 first-author papers at conferences or journals such as AAAI 2026 and IJCNN 2024, and have also published 2 co-author papers, such as in RSS 2026.

My research interests focus on Physical Constitutive Representation Learning (Physical Intelligence & Interactive World Model) and 3D Asset Generation for Game Physics Engines (PBR Generation & Feed-Forward World Building). I am seeking research collaborations, feel free to exchange ideas.

Haoqin Hong GitHub stats
Chinese signature English signature
Email Email: HaoqinHong@outlook.com (Preferred)   haoqinhong@mail.ustc.edu.cn   Phone/WeChat: (+86) 18728425682
Address Tianchen Road, High-tech West District, Chengdu, Sichuan Province, China, 611731


News

  • [2026.05]   I will start a research internship at miHoYo / HoYoverse (Jul 2026 - Aug 2026).
  • [2026.04]   One co-authored paper, developed in collaboration with Xense Robotics, was accepted to RSS 2026. Congratulations to Zhemeng Zhang @ MMLab - HKU.
  • [2026.02]   I will start a research internship at UBISOFT La Forge (Feb 2026 - Jul 2026).
  • [2026.01]   I have been admitted to the Tencent Game Engine Graphics Research Talent Program.
  • [2025.11]   One first-author paper was accepted by AAAI 2026.
  • [2025.09]   I will start a research internship at iFLYTEK Spark-LLM (Sep 2025 - Jan 2026).
  • [2025.09]   One co-authored paper, developed in collaboration with JD Explore Academy, was accepted by Neurocomputing 2025.
  • [2024.03]   One first-author paper was accepted by IEEE WCCI - IJCNN 2024 Oral.

Publications & Awards


Publications

  (* Equal contribution, † Corresponding author, ‡ Project leader)

A total of 6 publications, including 4 as the first author.

Physical Constitutive Representation Learning (Physical Intelligence & Interactive World Model)
Physics-Informed Deformable Gaussian Splatting overview
AAAI 2026

Physics-Informed Deformable Gaussian Splatting: Towards Unified Constitutive Laws for Time-Evolving Material Field.

arXiv Paper Project Page Poster PDF GitHub stars for Physics-Informed Deformable Gaussian Splatting

Haoqin Hong*, Ding Fan*, Fubin Dou, Zhi-Li Zhou, Haoran Sun, Congcong Zhu†, Jingrun Chen†.

AAAI Conference on Artificial Intelligence (AAAI 2026), Jan 2026.

Dynamic 3D Reconstruction Physical Intelligence
Morphtwin method framework
Under Review

MorphTwin: Discovering and Morphing Material Responses from Videos for Interactive Physical Twins.

Haoqin Hong*, Ding Fan*, Fubin Dou*, Tianyu Huang*‡, Zhemeng Zhang, Yuzhuo Chen, Congcong Zhu†, Gerhard Petrus Hancke, Jingrun Chen†, Rynson WH Lau.

Physically Interactive World Model Physical Intelligence
Physwonder method framework
Under Review

PhysWonder: Building Simulation-Ready Worlds Where Deformation Dynamics Reveal Constitutive Response.

Haoqin Hong*, Haoxiang Zhan*, Haoran Sun*, Tianyu Huang*‡, Zhemeng Zhang, Yuzhuo Chen, Liuzhou Zhang, Congcong Zhu†, Gerhard Petrus Hancke, Jingrun Chen†, Rynson WH Lau.

Physically Interactive World Model Physical Intelligence
TouchGuide insight
RSS 2026
In collaboration with Xense Robotics

TouchGuide: Inference-Time Steering of Visuomotor Policies via Touch Guidance.

arXiv Paper Project Page

Zhemeng Zhang, Jiahua Ma, Xincheng Yang, Xin Wen, Yuzhi Zhang, Boyan Li, Yiran Qin‡, Jin Liu, Can Zhao, Li Kang, Haoqin Hong, Zhenfei Yin, Philip Torr, Hao Su, Ruimao Zhang, Daolin Ma†.

Robotics: Science and Systems (RSS 2026), July 2026.

Embodied AI Tactile-Based VLA Model
Other Paper

CCSPNet-Joint: Efficient Joint Training Method for Traffic Sign Detection Under Extreme Conditions.

Haoqin Hong, Yue Zhou†, Xiangyu Shu, Xiaofang Hu. arXiv PaperGitHub stars for CCSPNet-Joint

IEEE International Joint Conference on Neural Networks (WCCI - IJCNN 2024 Oral), June 2024.

Attaining Hardware-Efficient Inference in Memristor-Based Transformer Accelerator via Network Redesign.

Junze Xu, Haoqin Hong, Yue Zhou†, Xiaofang Hu, Shukai Duan.

Neurocomputing 2025, Sep 2025. In collaboration with JD Explore Academy


Selected Awards

Honors and Awards

  1. [2025.10]   USTC First-Class Master's Academic Scholarship.
  2. [2025.06]   Outstanding Individual in Innovation Capability in Chongqing.
  3. [2025.06]   Outstanding Graduates in SWU.
  4. [2025.06]   Outstanding Undergraduate Thesis of SWU.
  5. [2025.03]   SWU Hanhong Foundation Student Success Scholarship. (One of the Highest Graduation Honors)
  6. [2024.06]   SWU First Class Scholarship.


Competition Awards

  1. 🥉 Bronze Medal in Kaggle Research Competition: NeurIPS - Open Polymer Prediction 2025.
  2. 🥉 Bronze Medal in Kaggle Research Competition: CVPR 2025 Workshop - Image Matching Challenge.
  3. 🥉 Bronze Medal in Kaggle Research Competition: Google - Fast or Slow? Predict AI Model Runtime.
  4. 🏅 National First Prize in the DJI RoboMaster University League.
  5. 🏅 National First Prize in the China Robotics and Artificial Intelligence Competition.
  6. 🥈 National Second Prize in the China Undergraduate Mathematical Contest in Modeling.
  7. 🥉 National Third Prize in the "Challenge Cup" Specialized Competition - Huawei Track.
  8. 🏅 Provincial First Prize in the National Undergraduate Electronics Design Contest.
RoboMaster robot project
SWU RoboMaster Lab Ex Leader

Real-Time Robotic Object Detection and LiDAR 3D SLAM for Navigation.

From left to right in the photo: Bohan Ma @ ZJU Ph.D, Xiangyu Shu @ SCUT Ph.D, Haoqin Hong @ USTC M.Phil, Chengyu Fang @ TsinghuaU M.Eng, Jiesen Zhao @ BUAA M.Eng, Xinke Zhang @ XDU M.Eng.

-->

From 2023 to 2025, I served as Project Manager and Algorithm Group Leader, we won First Prize in the DJI RoboMaster University League, with 3rd Place in the Southwest Regional. Certifications


Education Experience

  • USTC Logo
    University of Science and Technology of China (USTC)
    School of Artificial Intelligence and Data Science | 2025.9 - 2028.7
    M.Phil in Intelligence Science and Technology - Artificial Intelligence
    Postgraduate Recommendation | Advisor: Prof. Jingrun Chen
    中国科学技术大学人工智能与数据科学学院智能科学与技术学术型硕士
  • SWU Logo
    Southwest University (SWU)
    Top Talent Program - Yuan Longping Class | 2021.9 - 2025.7
    B.Eng in Computer Science and Technology
    Average Score: 91.3 / 100 | Advisor: Prof. Xiaofang Hu
    西南大学袁隆平书院（拔尖人才培养计划）计算机科学与技术工学学士
  • UCLA Logo
    University of California, Los Angeles (UCLA)
    Visiting Student in Data Science | 2022.9 - 2023.1
    Jointly funded by the Southwest University International Office Overseas Exchange & Study Special Grant and the Yuan Longping College Special Scholarship for Overseas Visiting Study (First-Class), earning a GPA of 4.0 / 4.0
    加州大学洛杉矶分校数据科学项目访问学生

Internships and Projects

Internship Experience

  • Mihoyo Logo
    miHoYo / HoYoverse (Shanghai) · Fundamental Technology Research Team
    Researcher (Intern) in Game Engine AI Technology | 2026.7 - 2026.8
    米哈游（上海）科技有限公司基础技术研究团队游戏引擎 AI 技术研究员
  • Ubisoft Logo
    UBISOFT Global Research & Development (China Studio) · UBISOFT La Forge Team
    Student Researcher in World Building & Rendering | 2026.2 - 2026.7
    育碧娱乐软件公司全球研发部门（中国工作室）La Forge 团队世界重建和渲染方向学生研究员
  • iFlyTek Logo
    iFLYTEK (Hefei) Research & Development Group · Spark-LLM Foundation Model Team
    Assistant Research Algorithm Engineer in Multimodal-LLMs Post-Training | 2025.9 - 2026.1
    讯飞星火大模型基座模型团队多模态大模型后训练方向助理算法研究工程师

Presentative Research Projects

  • Tencent IEG Logo
    Advanced Game Technology Department, Tencent Interactive Entertainment Group (IEG)
    Tencent Game Engine Graphics Research Talent Program | 2026.1 - 2026.7
    Applications of World Models based on 3DGS in Game UGC Development
    腾讯游戏引擎图形学实践精英人才培养计划
  • USTC-Suzhou High-Level Institute Logo
    Suzhou Institute for Advanced Research, USTC
    Leader of Innovation Training Program | 2026.6 - Present
    Towards World Models: Physics-Aligned Generative Platform for Spatial Intelligence
    中国科学技术大学苏州高等研究院创新创业项目负责人
  • National Astronomical Observatory Logo
    National Astronomical Observatory, Chinese Academy of Sciences
    Leader of Innovation Training Program | 2023.3 - 2024.7
    Generative Astronomical Multimodal Model for IR-Optical Cross-Retrieval
    中国科学院大学生创新实践训练项目（"科创计划"）负责人


Open-Source Projects

  1. Awesome-Physically-Interactive-World-Models   Github stars
  2. RoboMaster-SLAM: Point-LIO & MID-360 Sentinel Navigation Solution   Github stars

Additional Information


Research Collaborators

  • Congcong Zhu [homepage]
    Associate Researcher at USTC (Suzhou) 3D Vision, Embodied AI
  • Tianyu Huang [homepage]
    Researcher (TopMinds Program) at Xiaoyi-AI Lab, Huawei Shanghai World Models, Video Generation
  • Zhi-Li Zhou [homepage]
    Ph.D in Physics & Mathematics at UIUC Theoretical Physics
  • Zhemeng Zhang [homepage]
    Ph.D in Robotics at MMLab@HKU Tactile-Based Robotics Manipulation
  • Yuzhuo Chen [homepage]
    M.Eng in CS at USTC Video Generation, AIGC Safety