Tai Hoang

PhD Student in Machine Learning and Robotics at Karlsruhe Institute of Technology.

prof_pic.jpg

4th Floor InformatiKOM 1.

Adenauerring 12, Karlsruhe

I started my PhD at the Autonomous Learning Robot (ALR) group in June 2023 at KIT, under the supervision of Prof. Gerhard Neumann. Before that, I completed my Master at the Technical University of Munich and my Bachelor at the University of Information Technology in Vietnam, both majoring in Computer Science.

My research interest includes:

  • Graph Neural Networks
  • Physical Modelling
  • Reinforcement Learning
  • Deformable Object Manipulation

Selected publications

(* denotes equal contribution)
  1. ICLR EurIPS 25 Workshop
    Improving Long-Range Interactions in Graph Neural Simulators via Hamiltonian Dynamics
    Tai Hoang, Alessandro Trenta*, Alessio Gravina*, and 4 more authors
    The Fourteenth International Conference on Learning Representations, 2026
    arXiv PDF Website
  2. NeurIPS
    MaNGO — Adaptable Graph Network Simulators via Meta-Learning
    Philipp Dahlinger, Tai Hoang, Denis Blessing, and 2 more authors
    In The Thirty-ninth Annual Conference on Neural Information Processing Systems, 2025
    PDF Website
  3. ICLR Oral
    Geometry-aware RL for Manipulation of Varying Shapes and Deformable Objects
    Tai Hoang, Huy Le, Philipp Becker, and 2 more authors
    In The Thirteenth International Conference on Learning Representations, 2025
    Oral Presentation [Top 1.8%]
    PDF Website
  4. RA-L
    Enhancing Exploration With Diffusion Policies in Hybrid Off-Policy RL: Application to Non-Prehensile Manipulation
    Huy Le, Tai Hoang, Miroslav Gabriel, and 2 more authors
    IEEE Robotics and Automation Letters, 2025
    DOI PDF Website