Hoang Trieu Vy LE

2025 –

I joined Beink Dream as a Research Scientist in Paris, where I architect end-to-end agentic AI systems. I work on multiple challenging problems — from generative images with flow to building multi-modal systems that maintain a structured representation of 2D, 3D scenes and CAD modalities.

2024 – 2025

I was a Research Engineer at CEA – DIGITEO Labs in Saclay, where I worked on lightweight learning models for 3D CT reconstruction — building physics-consistent scene representations from sparse, noisy measurements and limited high-dimensional observations.

2020 – 2023

My PhD at ENS Lyon was focused on variations of the Mumford-Shah functional for interface detection in degraded images, bridging proximal algorithms and unrolled deep architectures [take a look] under the supervision of Prof. Nelly Pustelnik and Dr. Marion Foare. Along the way I spent a year at UC Louvain (2020–2021) designing scalable accelerated algorithms for joint image restoration and edge detection on large-scale physics experiment images.

I also taught Introduction to Machine Learning and Optimisation at EPITA, and Machine Learning & Optimization hands-on courses at ENS Lyon.

2015 – 2020

I studied at INSA Toulouse where I earned my Master of Engineering in Applied Mathematics, majoring in Mathematical Modelling and Numerical Analysis.

CV

Research Interests

• Machine learning for perception and physical systems
  • Multimodal LLMs
  • World models, real2sim2real transfer, physical AI
  • Reinforcement learning for robot control and human modeling
  • Generative models
• Inverse problems and optimization
  • Non-smooth and non-convex optimization, proximal algorithms
  • Unrolled and physics-consistent deep architectures
  • Mumford–Shah models, joint restoration and edge detection
• Applications
  • Robotics and embodied agents
  • Computer-aided design, 3D reconstruction and scene understanding
  • Tomographic imaging, 3D CT reconstruction
  • Large-scale physics-experiment and scientific imaging

Recent Works

Publications

Ph.D Thesis

Supervisors: Prof. Nelly Pustelnik, Dr. Marion Foare

Reviewers: Prof. Caroline Chaux, Assoc. Prof. Matthieu Kowalski

Examiners: Prof. Jean-François Aujol, Prof. Elie Bretin, Prof. Luca Calatroni, Prof. Marc Sebban

Talks

Teaching

For Fun

Polyverse — a hobby game I build on weekends. A low-poly 3D real-time strategy game in Godot, where time has shattered into crystal shards and each shard is one frozen age of civilization.