An Thai Le

An Thai Le

Assistant Professor @ VinUniversity · Visiting Professor @ TU Darmstadt

I work at the intersection of Robotics and Machine Learning. My research scales motion planning and policy learning to long-horizon, high-dimensional, and multimodal problems - mostly through tensor search (GPU-batched search and optimization over plan tensors) and by pairing algorithmic structure with generative models (diffusion, flow matching). Lately, mostly humanoid loco-manipulation.

On weekends I write JAX/PyTorch simulators for curved spacetimes - Kerr black holes, the Penrose process, warp-drive energy conditions - because the math is too beautiful to ignore! :)

News

Research

I try to scale planning to settings classical methods struggle with - long horizons, high-dimensional state spaces, large plan sets, multi-agent - by treating search as a batched tensor operation and by leaning on generative models where structure runs out. Most current work targets humanoid loco-manipulation.

Tensor Search & Batched Planning

Casting search and trajectory optimization as batched tensor operations on the GPU - the spine of my thesis and most of my recent planners.

Diffusion & Flow Matching for Motion

Using diffusion and flow matching as priors over trajectories and policies, especially when the solution landscape is multimodal and gradients alone are not enough.

Humanoid Loco-manipulation

Whole-body RL and model-based control for humanoids in contact-rich tasks. Ongoing - many things still fall over.

VLA / VLM for Robotics

Data-efficient adaptation of vision-language(-action) models for grasping and manipulation - currently chasing better grounding from fewer demonstrations.

Optimal Transport & Gradient Flows

Borrowing entropic OT and gradient-flow machinery to design planners, blend policies, and train networks where standard gradients break down.

Numerical General Relativity

A weekend hobby: JAX/PyTorch CUDA simulators for processes in curved spacetime - Kerr orbits, Penrose extraction, and warp-drive energy conditions.

Selected Publications

* indicates co-first or co-last authors. See also my Google Scholar profile.

Experience

Visiting Professor

Oct 2025 - Present · Darmstadt, Germany

Co-advising MSc and PhD students at IAS on robot learning research.

Assistant Professor

Oct 2025 - Present · Hanoi, Vietnam

Building a research group on efficient learning and planning for robotics loco-manipulation, designing fundamental algorithms and methods.

Director of Foundation AI

Aug 2025 - Present · Hanoi, Vietnam
  • RL stack for high-payload humanoid locomotion
  • Humanoid VLA architecture and training recipe
  • Model optimization and edge-deployment toolchain

Ph.D. in Computer Science

2022 - 2025 · Darmstadt, Germany

Thesis: Tensor Search Methods for Vectorizing Motion Planning - supervised by Prof. Jan Peters.

Research Intern

May 2020 - Dec 2020 · Renningen, Germany

Worked on forceful imitation learning applied to E-bike assembly tasks, hosted by Dr. Meng Guo in the robotics team.

M.Sc. Information Technology

2019 - 2021 · Stuttgart, Germany

Thesis: Learning task-parameterized Riemannian motion policies - supervised by Dr. Jim Mainprice & Dr. Meng Guo. Graduated First class. Info-Preis for Best Diploma Award. Sony Research Award. Deutschlandstipendium.

Research Assistant

Nov 2019 - Apr 2020 · Stuttgart, Germany

Implemented back-end functionalities in the DASH project; maintained and configured HPC systems.

B.Eng. Electrical Engineering and Information Technology

2015 - 2019 · Frankfurt, Germany

Thesis: Approaches to solve kidnapped robot problem. Graduated First class. DAAD Scholarship. AmCham Scholarship. eSilicon Scholarship.

Engineer Intern

Jan 2017 - May 2017 · Ho Chi Minh City, Vietnam

Designed data analysis systems for high-volume manufacturing unit-test data; validated and reported quality of Intel Thunderbolt product manufacturing line.

Teaching

  • Reinforcement Learning TU Darmstadt · SS 2022
  • Statistical Machine Learning TU Darmstadt · SS 2023, WS 2023/24, SS 2024, WS 2024/25
  • Probabilistic Methods for Computer Science TU Darmstadt · WS 2024/25
  • Robot Learning Integrated Project / Expert Lab / Mechatronics TU Darmstadt · WS 2024/25

People

Masters Students

Dinh Van The Long
Dinh Van The Long

VinRobotics Residents

Trinh Thi Cuc
Trinh Thi Cuc
TD
Dang Truong Duy
Le Anh Chien
Le Anh Chien
ND
Nguyen Viet Duong
Ly Phuc Thanh
Ly Phuc Thanh
PD
Phuong Tuan Dat
Do Tan Dung
Do Tan Dung
Ho Thinh Hung
Ho Thinh Hung

Alumni

Magnus Dierking
Magnus Dierking
Caio Freitas
Caio Freitas
QS
Qiao Sun
DA
Dennis Andric
Sebastian Zach
Sebastian Zach

Current Collaborators

Zachary Kingston
Purdue University
Meng Guo
Peking University
Ngo Anh Vien
VinRobotics

Academic Service

Reviewer - Conferences & Area Chair

Area Chair: RLC
Reviewer: IROS, ICRA, R:SS, CoRL, L4DC, NeurIPS, ICML, ICLR, AAAI

Reviewer - Journals

IEEE RA-L, IEEE T-RO, Neurocomputing, TMLR, Frontiers in Robotics and AI