Quentin Le Lidec

I am a postdoctoral researcher at the Courant Institute of Mathematical Sciences at New York University, working with Yann LeCun on world models for robotics. My current research is focused on using AI to solve problems in the physical world.

I'm committed to open-source development, contributing to Pinocchio and Simple to make fundamental robotics tools accessible to all.

Prior to that, I received my PhD in computer science from ENS Paris where I was working under the supervision of Justin Carpentier, Cordelia Schmid and Ivan Laptev. Even before that, I received an engineering degree from École Polytechnique and an MSc in Mathematics, Computer Vision, and Machine Learning from École Normale Supérieure Paris-Saclay.

Email  /  Scholar  /  Github  /  LinkedIn

News

• Feb 2026: I will be at the World Modeling Workshop!
• Oct 2025: I received the Best Thesis Award from the GDR Robotique!
• Dec 2024: I defended my PhD on Differentiable optimization for robotics: simulation, learning and control.
• Nov 2024: I organized a workshop on Differentiable Optimization Everywhere: Simulation, Estimation, Learning, and Control at CORL'24 in Munich!

Research

My research interests lie at the intersection of machine learning, optimization, and computer vision, and their applications to robotics. The complete list of my publications can be found on my Google Scholar profile.

Selected Publications

Physical Simulation

A unified and efficient algorithmic solution for computing analytical derivatives of robotic simulators, achieving state-of-the-art timings from 5 microseconds for a 7-dof manipulator up to 95 microseconds for 36-dof humanoid.

A unified approach to solving contact interactions using ADMM and proximal algorithms, handling both compliant and rigid contact interfaces with automatic hyperparameter adaptation.

Comprehensive survey and benchmark of contact models in robotics simulators, exposing physical relaxations and computational limitations with open-source implementations.

World Models

Enhancing action planning in JEPAs by shaping the representation space to approximate goal-conditioned value functions as distances between state embeddings.

Code

I contribute to several open-source robotics libraries, making differentiable physics and world model tools accessible for the robotics and ML communities.

A highly efficient library for differentiable simulation of multibody systems with contacts.

A fast and flexible implementation of rigid body dynamics algorithms and their analytical derivatives.

A framework for world model research enabling reproducible data collection, flexible model training, and comprehensive evaluation tools.

Miscellanea

Academic Service:

Reviewer: NeurIPS, ICML, RSS, ICRA, IROS, T-RO, RA-L, L4DC, Humanoids Area Chair: ICRA

Workshop: Differentiable Optimization Everywhere: Simulation, Estimation, Learning, and Control at CORL'24

Teaching: Teaching assistant for "Convex optimization" course at MSc MVA, ENS Paris-Saclay.

All Publications

Enhancing action planning in JEPAs by shaping the representation space to approximate goal-conditioned value functions as distances between state embeddings.

A novel framework combining diffusion policy with trajectory optimization, using gradient-based solvers to generate locally optimal trajectories and leveraging their feedback gains to enrich Sobolev training with first-order information for more efficient policy learning.

Optimization is ubiquitous in modern robotics. This thesis aims to bring fundamental robotics tools to the differentiable programming paradigm, looking at robot simulation through the lens of numerical optimization techniques and proposing approaches for learning controllers.

A unified and efficient algorithmic solution for computing analytical derivatives of robotic simulators, achieving state-of-the-art timings from 5 microseconds for a 7-dof manipulator up to 95 microseconds for 36-dof humanoid.

A unified approach to solving contact interactions using ADMM and proximal algorithms, handling both compliant and rigid contact interfaces with automatic hyperparameter adaptation.

Accelerated collision detection by establishing GJK as a Frank-Wolfe algorithm and introducing Nesterov acceleration, leading to up to two times faster computation.

Algorithmic correction of the RaiSim contact algorithm to properly handle the maximum dissipation principle for more physically-consistent simulation.

Comprehensive survey and benchmark of contact models in robotics simulators, exposing physical relaxations and computational limitations with open-source implementations.

Combining reinforcement learning and trajectory optimization using Sobolev learning and augmented Lagrangian techniques to learn global control policies faster.

Generic approach to compute derivatives of collision detection for convex shapes using randomized smoothing techniques, with microsecond computation times.

Showing collision detection is fundamentally a convex optimization problem and introducing accelerated collision detection using Nesterov acceleration.

Leveraging randomized smoothing to estimate gradients in optimization problems involving non-smooth physical processes for mesh reconstruction and optimal control.

Introducing Randomized Differential Dynamic Programming (R-DDP) to handle nonsmooth dynamics with contacts and friction in a sample-efficient way.

Studying differentiable renderers through randomized optimization and perturbed optimizers, with applications to 6D pose estimation and 3D mesh reconstruction.

Differentiable simulation framework for accurate estimation of friction coefficients and object masses using staggered projections and analytical derivatives.