Valentin Duruisseaux NVIDIA

Publications

Research on physics-informed machine learning for accelerated simulation and design, together with earlier works on numerical geometric integration and its connections to optimization and dynamics learning.

Google Scholar ↗ Semantic Scholar ↗ ResearchGate ↗ DBLP ↗

35 research works

Year
Type

Doctoral thesis

UC San Diego · Advisor: Melvin Leok

Symplectic Numerical Integration at the service of Accelerated Optimization and Structure-Preserving Dynamics Learning

Valentin Duruisseaux, 2023

Read thesis UC eScholarship

Scientific machine learning

Fourier Neural Operators Explained: A Practical Perspective

Valentin Duruisseaux, Jean Kossaifi, Anima Anandkumar

arXiv preprint, 2025 · revised 2026

arXiv Code

Principled Approaches for Extending Neural Architectures to Function Spaces for Operator Learning

Julius Berner*, Miguel Liu-Schiaffini*, Jean Kossaifi, Valentin Duruisseaux, Boris Bonev, Kamyar Azizzadenesheli, Anima Anandkumar (*equal contribution)

Nature Machine Intelligence 8:1173–1181, 2026

DOI arXiv Code

A Library for Learning Neural Operators

Jean Kossaifi*, Nikola Kovachki*, Zongyi Li*, David Pitt*, Miguel Liu-Schiaffini, Robert J. George, Boris Bonev, Kamyar Azizzadenesheli, Julius Berner, Valentin Duruisseaux, Anima Anandkumar (*equal contribution)

Journal of Machine Learning Research 27(205):1–6, 2026

JMLR arXiv Code

Self-Similar Singularity of the Euler Equations on R3

Adarsh Ganeshram*, Valentin Duruisseaux*, Anima Anandkumar (*equal contribution)

Preprint, 2026

arXiv

Stability Framework for the Singularity of the Euler Equations on R3

Valentin Duruisseaux*, Adarsh Ganeshram*, Robert J. George, Anima Anandkumar (*equal contribution)

Preprint, 2026

arXiv

Counterfactual Predictions in Scientific Emulators Without Controlled Experiments

Dingling Yao, Kahaan Gandhi, Valentin Duruisseaux, Boris Bonev, Francesco Locatello, Anima Anandkumar

Preprint, 2026

arXiv

Equation Recast for Canonical Operator Learning Across Parametric PDEs

Qiyun Cheng, Valentin Duruisseaux, Cesar F. Clauser, Md Hossain Sahadath, Huihua Yang, Shaowu Pan, Nathaniel Ferraro, Anima Anandkumar, Wei Ji, Cristina Rea

Preprint, 2026

arXiv

Inverse Design of Quantum Control Sequences with Fourier Neural Operators

Anastasia Pipi, Valentin Duruisseaux, Emily Been, Xuecheng Tao, Taylor L. Patti, Anima Anandkumar, Prineha Narang

Preprint, 2026

arXiv

Learnable Splines for Unstructured Neural Operators

Vignesh Gopakumar, Zhuoyuan Wang, Ander Gray, Valentin Duruisseaux, Josh Williams, William M. E. Ellis, Nuno Nobre, Matthew Field, James Panayis, Alexander I. Blair, Andrew Davis, Stanislas Pamela, Robert Akers, Marc Peter Deisenroth, Anima Anandkumar

Preprint, 2026

arXiv

AI-Accelerated Gyrokinetic Predictions of Turbulent Transport for Stellarator Design Optimization and Experimental Planning

R. Michael Churchill, Matt Landreman, Jong Youl Choi, Byoungchan Jang, Rory Conlin, Noah Mandell, Anima Anandkumar, Valentin Duruisseaux, Jeffrey Larson, Dario Panici, Yigit Gunsur Elmacioglu, Jai Sachdev, Tony Qian

Preprint, 2026

arXiv

Performance of Neural Operator Baselines on 'The Well' Dataset

Yash Pincha, Andy Dimnaku, Andrew Chiang, Adarsh Ganeshram, Valentin Duruisseaux, Anima Anandkumar

Preprint, 2026

arXiv Code

NOBLE - Neural Operator with Biologically-informed Latent Embeddings to Capture Experimental Variability in Biological Neuron Models

Luca Ghafourpour, Valentin Duruisseaux*, Bahareh Tolooshams*, Philip H. Wong, Costas A. Anastassiou, Anima Anandkumar (*equal contribution)

Advances in Neural Information Processing Systems 38, 2025

DOI OpenReview arXiv Code

Enabling Automatic Differentiation with Mollified Graph Neural Operators

Ryan Y. Lin, Julius Berner, Valentin Duruisseaux, David Pitt, Daniel Leibovici, Jean Kossaifi, Kamyar Azizzadenesheli, Anima Anandkumar

Transactions on Machine Learning Research, 2025

OpenReview arXiv Code

FC-PINO: High Precision Physics-Informed Neural Operators via Fourier Continuation

Adarsh Ganeshram, Valentin Duruisseaux, Haydn Maust, Zongyi Li, Yixuan Wang, Daniel Leibovici, Oscar Bruno, Thomas Hou, Anima Anandkumar

arXiv preprint, originally 2022 · revised 2026

arXiv Code

Fourier Neural Operators for Fast Simulation and Inverse Design of Second-Harmonic Generation in TFLN Waveguide

Valentin Duruisseaux*, Robert M. Gray*, Siyuan Jiang*, Selina Zhou, Robert J. George, Kamyar Azizzadenesheli, Alireza Marandi, Anima Anandkumar (*equal contribution)

NeurIPS Workshop on Machine Learning and the Physical Sciences, 2025

PDF

Inverse Design with Fourier Neural Operators for Quantum System Control

Anastasia Pipi, Nivedha Gopinath, Valentin Duruisseaux, Myrl G. Marmarelis, Taylor L. Patti, Brucek Khailany, Prineha Narang, Anima Anandkumar

NeurIPS Workshop on Machine Learning and the Physical Sciences, 2025

OpenReview PDF

Boundary-Augmented Neural Operators for Better Generalization to Unseen Geometries

Jiayi Zhou, Valentin Duruisseaux, Daniel Zhengyu Huang, Anima Anandkumar

NeurIPS Workshop: AI4Science, 2025

OpenReview

Coarse-to-Fine 3D MRI Reconstruction via 3D Neural Operators

Armeet Singh Jatyani*, Jiayun Wang*, Ryan Y. Lin, Valentin Duruisseaux, Anima Anandkumar (*equal contribution)

NeurIPS Workshop on Imageomics, 2025

OpenReview

FG-ConvNO: A Geometry-Aware Neural Operator for Propeller CFD Prediction

Yichen Di, Valentin Duruisseaux, Di Zhou, Xinyi Li, Daniel Leibovici, Jean Kossaifi, Anima Anandkumar

AAAI AI2ASE Workshop, 2026

arXiv PDF

Towards Enforcing Hard Physics Constraints in Operator Learning Frameworks

Valentin Duruisseaux*, Miguel Liu-Schiaffini*, Julius Berner, Anima Anandkumar (*equal contribution)

ICML AI for Science Workshop, 2024

OpenReview Code

Projected Neural Differential Equations for Learning Constrained Dynamics

Alistair White, Anna Büttner, Maximilian Gelbrecht, Valentin Duruisseaux, Niki Kilbertus, Frank Hellmann, Niklas Boers

arXiv preprint, 2024 · revised 2026

arXiv

An Operator Learning Framework for Spatiotemporal Super-resolution of Scientific Simulations

Valentin Duruisseaux, Amit Chakraborty

arXiv preprint, 2023 · revised 2024

arXiv Code

Approximation of Nearly-Periodic Symplectic Maps via Structure-Preserving Neural Networks

Valentin Duruisseaux, Joshua W. Burby, Qi Tang

Scientific Reports 13, 8351, 2023 · Collection on Physics-informed Machine Learning and its Real-world Applications

DOI arXiv Code

Lie Group Forced Variational Integrator Networks for Learning and Control of Robot Systems

Valentin Duruisseaux, Thai P. Duong, Melvin Leok, Nikolay Atanasov

Proceedings of the 5th Annual Learning for Dynamics and Control Conference, PMLR 211:731–744, 2023

PMLR arXiv Code

Accelerated optimization via geometric numerical integration

Adaptive Hamiltonian Variational Integrators and Applications to Symplectic Accelerated Optimization

Valentin Duruisseaux, Jeremy Schmitt, Melvin Leok

SIAM Journal on Scientific Computing 43(4):A2949–A2980, 2021

DOI arXiv

A Variational Formulation of Accelerated Optimization on Riemannian Manifolds

Valentin Duruisseaux, Melvin Leok

SIAM Journal on Mathematics of Data Science 4(2):649–674, 2022

DOI arXiv

Variational Accelerated Optimization on Riemannian Manifolds

Valentin Duruisseaux, Melvin Leok

International Symposium on Nonlinear Theory and Its Applications, IEICE Proceedings Series 71 (B1L-D-03):240–241, 2022

DOI

Accelerated Optimization on Riemannian Manifolds via Discrete Constrained Variational Integrators

Valentin Duruisseaux, Melvin Leok

Journal of Nonlinear Science 32(4):42, 2022

DOI arXiv

Accelerated Optimization on Riemannian Manifolds via Projected Variational Integrators

Valentin Duruisseaux, Melvin Leok

Preprint, 2022

arXiv

Time-adaptive Lagrangian Variational Integrators for Accelerated Optimization

Valentin Duruisseaux, Melvin Leok

Journal of Geometric Mechanics 15(1):224–255, 2023

DOI arXiv

Practical Perspectives on Symplectic Accelerated Optimization

Valentin Duruisseaux, Melvin Leok

Optimization Methods and Software 38(6):1230–1268, 2023

DOI arXiv Code

Riemannian optimization

Practical Structured Riemannian Optimization with Momentum by using Generalized Normal Coordinates

Wu Lin, Valentin Duruisseaux, Melvin Leok, Frank Nielsen, Mohammad Emtiyaz Khan, Mark Schmidt

NeurIPS Workshop on Symmetry and Geometry in Neural Representations, 2022

OpenReview Code

Simplifying Momentum-based Positive-definite Submanifold Optimization with Applications to Deep Learning

Wu Lin, Valentin Duruisseaux, Melvin Leok, Frank Nielsen, Mohammad Emtiyaz Khan, Mark Schmidt

International Conference on Machine Learning, PMLR 202:21026–21050, 2023

PMLR arXiv Code

Numerical bifurcation analysis

Bistability, Bifurcations and Chaos in the Mackey–Glass Equation

Valentin Duruisseaux, Antony R. Humphries

Journal of Computational Dynamics 9(3):421–450, 2022

DOI arXiv Code