Ruben Ohana

39 papers A* 8A 1Misc 2Journal 26Unranked 2
YearRankTypeTitle / Venue / Authors
2026 J jnl
On the Value of Tokeniser Pretraining in Physics Foundation Models.
CoRR
Hadi Sotoudeh, Payel Mukhopadhyay, Ruben Ohana, Michael McCabe, Neil D. Lawrence, Shirley Ho, Miles D. Cranmer
2025 J jnl
Controllable Patching for Compute-Adaptive Surrogate Modeling of Partial Differential Equations.
CoRR
Payel Mukhopadhyay, Michael McCabe, Ruben Ohana, Miles D. Cranmer
2025 J jnl
Lost in Latent Space: An Empirical Study of Latent Diffusion Models for Physics Emulation.
CoRR
François Rozet, Ruben Ohana, Michael McCabe, Gilles Louppe, François Lanusse, Shirley Ho
2025 J jnl
Predicting partially observable dynamical systems via diffusion models with a multiscale inference scheme.
CoRR
Rudy Morel, Francesco Pio Ramunno, Jeff Shen, Alberto Bietti, Kyunghyun Cho, Miles D. Cranmer, Siavash Golkar, Olexandr Gugnin, Géraud Krawezik, Tanya Marwah, Michael McCabe, Lucas Meyer, Payel Mukhopadhyay, Ruben Ohana, Liam Holden Parker, Helen Qu, François Rozet, K. D. Leka, François Lanusse, David Fouhey, Shirley Ho
2025 J jnl
TC-LoRA: Temporally Modulated Conditional LoRA for Adaptive Diffusion Control.
CoRR
Minkyoung Cho, Ruben Ohana, Christian Jacobsen, Adityan Jothi, Min-Hung Chen, Z. Morley Mao, Ethem Can
2025 J jnl
Universal Spectral Tokenization via Self-Supervised Panchromatic Representation Learning.
CoRR
Jeff Shen, François Lanusse, Liam Holden Parker, Ollie Liu, Tom Hehir, Leopoldo Sarra, Lucas Meyer, Micah Bowles, Sebastian Wagner-Carena, Helen Qu, Siavash Golkar, Alberto Bietti, Hatim Bourfoune, Nathan Cassereau, Pierre Cornette, Keiya Hirashima, Géraud Krawezik, Ruben Ohana, Nicholas Lourie, Michael McCabe, Rudy Morel, Payel Mukhopadhyay, Mariel Pettee, Bruno Régaldo-Saint Blancard, Kyunghyun Cho, Miles D. Cranmer, Shirley Ho
2025 J jnl
Walrus: A Cross-Domain Foundation Model for Continuum Dynamics.
CoRR
Michael McCabe, Payel Mukhopadhyay, Tanya Marwah, Bruno Régaldo-Saint Blancard, François Rozet, Cristiana Diaconu, Lucas Meyer, Kaze W. K. Wong, Hadi Sotoudeh, Alberto Bietti, Irina Espejo, Rio Fear, Siavash Golkar, Tom Hehir, Keiya Hirashima, Géraud Krawezik, François Lanusse, Rudy Morel, Ruben Ohana, Liam Holden Parker, Mariel Pettee, Jeff Shen, Kyunghyun Cho, Miles D. Cranmer, Shirley Ho
2024 J jnl
Contextual Counting: A Mechanistic Study of Transformers on a Quantitative Task.
CoRR
Siavash Golkar, Alberto Bietti, Mariel Pettee, Michael Eickenberg, Miles D. Cranmer, Keiya Hirashima, Géraud Krawezik, Nicholas Lourie, Michael McCabe, Rudy Morel, Ruben Ohana, Liam Holden Parker, Bruno Régaldo-Saint Blancard, Kyunghyun Cho, Shirley Ho
2024 J jnl
Listening to the Noise: Blind Denoising with Gibbs Diffusion.
CoRR
David Heurtel-Depeiges, Charles C. Margossian, Ruben Ohana, Bruno Régaldo-Saint Blancard
2024 A* conf
Listening to the noise: Blind Denoising with Gibbs Diffusion.
ICML
David Heurtel-Depeiges, Charles Margossian, Ruben Ohana, Bruno Régaldo-Saint Blancard
2024 A* conf
MoMo: Momentum Models for Adaptive Learning Rates.
ICML
Fabian Schaipp, Ruben Ohana, Michael Eickenberg, Aaron Defazio, Robert M. Gower
2024 A* conf
Multiple Physics Pretraining for Spatiotemporal Surrogate Models.
NeurIPS
Michael McCabe, Bruno Régaldo-Saint Blancard, Liam Holden Parker, Ruben Ohana, Miles D. Cranmer, Alberto Bietti, Michael Eickenberg, Siavash Golkar, Géraud Krawezik, François Lanusse, Mariel Pettee, Tiberiu Tesileanu, Kyunghyun Cho, Shirley Ho
2024 J jnl
Optical training of large-scale Transformers and deep neural networks with direct feedback alignment.
CoRR
Ziao Wang, Kilian Müller, Matthew J. Filipovich, Julien Launay, Ruben Ohana, Gustave Pariente, Safa Mokaadi, Charles Brossollet, Fabien Moreau, Alessandro Cappelli, Iacopo Poli, Igor Carron, Laurent Daudet, Florent Krzakala, Sylvain Gigan
2024 A* conf
The Well: a Large-Scale Collection of Diverse Physics Simulations for Machine Learning.
NeurIPS
Ruben Ohana, Michael McCabe, Lucas Meyer, Rudy Morel, Fruzsina Julia Agocs, Miguel Beneitez, Marsha Berger, Blakesley Burkhart, Stuart B. Dalziel, Drummond B. Fielding, Daniel Fortunato, Jared A. Goldberg, Keiya Hirashima, Yan-Fei Jiang, Rich R. Kerswell, Suryanarayana Maddu, Jonah Miller, Payel Mukhopadhyay, Stefan S. Nixon, Jeff Shen, Romain Watteaux, Bruno Régaldo-Saint Blancard, François Rozet, Liam Holden Parker, Miles D. Cranmer, Shirley Ho
2024 J jnl
The Well: a Large-Scale Collection of Diverse Physics Simulations for Machine Learning.
CoRR
Ruben Ohana, Michael McCabe, Lucas Meyer, Rudy Morel, Fruzsina Julia Agocs, Miguel Beneitez, Marsha Berger, Blakesley Burkhart, Stuart B. Dalziel, Drummond B. Fielding, Daniel Fortunato, Jared A. Goldberg, Keiya Hirashima, Yan-Fei Jiang, Rich R. Kerswell, Suryanarayana Maddu, Jonah Miller, Payel Mukhopadhyay, Stefan S. Nixon, Jeff Shen, Romain Watteaux, Bruno Régaldo-Saint Blancard, François Rozet, Liam Holden Parker, Miles D. Cranmer, Shirley Ho
2023 J jnl
AstroCLIP: Cross-Modal Pre-Training for Astronomical Foundation Models.
CoRR
François Lanusse, Liam Holden Parker, Siavash Golkar, Miles D. Cranmer, Alberto Bietti, Michael Eickenberg, Géraud Krawezik, Michael McCabe, Ruben Ohana, Mariel Pettee, Bruno Régaldo-Saint Blancard, Tiberiu Tesileanu, Kyunghyun Cho, Shirley Ho
2023 A conf
Complex-to-Real Sketches for Tensor Products with Applications to the Polynomial Kernel.
AISTATS
Jonas Wacker, Ruben Ohana, Maurizio Filippone
2023 J jnl
MoMo: Momentum Models for Adaptive Learning Rates.
CoRR
Fabian Schaipp, Ruben Ohana, Michael Eickenberg, Aaron Defazio, Robert M. Gower
2023 J jnl
Multiple Physics Pretraining for Physical Surrogate Models.
CoRR
Michael McCabe, Bruno Régaldo-Saint Blancard, Liam Holden Parker, Ruben Ohana, Miles D. Cranmer, Alberto Bietti, Michael Eickenberg, Siavash Golkar, Géraud Krawezik, François Lanusse, Mariel Pettee, Tiberiu Tesileanu, Kyunghyun Cho, Shirley Ho
2023 J jnl
Removing Dust from CMB Observations with Diffusion Models.
CoRR
David Heurtel-Depeiges, Blakesley Burkhart, Ruben Ohana, Bruno Régaldo-Saint Blancard
2023 A* conf
Shedding a PAC-Bayesian Light on Adaptive Sliced-Wasserstein Distances.
ICML
Ruben Ohana, Kimia Nadjahi, Alain Rakotomamonjy, Liva Ralaivola
2023 J jnl
xVal: A Continuous Number Encoding for Large Language Models.
CoRR
Siavash Golkar, Mariel Pettee, Michael Eickenberg, Alberto Bietti, Miles D. Cranmer, Géraud Krawezik, François Lanusse, Michael McCabe, Ruben Ohana, Liam Holden Parker, Bruno Régaldo-Saint Blancard, Tiberiu Tesileanu, Kyunghyun Cho, Shirley Ho
2022 Misc conf
Adversarial Robustness by Design Through Analog Computing And Synthetic Gradients.
ICASSP
Alessandro Cappelli, Ruben Ohana, Julien Launay, Laurent Meunier, Iacopo Poli, Florent Krzakala
2022 J jnl
Complex-to-Real Random Features for Polynomial Kernels.
CoRR
Jonas Wacker, Ruben Ohana, Maurizio Filippone
2022 J jnl
Shedding a PAC-Bayesian Light on Adaptive Sliced-Wasserstein Distances.
CoRR
Ruben Ohana, Kimia Nadjahi, Alain Rakotomamonjy, Liva Ralaivola
2021 J jnl
Adversarial Robustness by Design through Analog Computing and Synthetic Gradients.
CoRR
Alessandro Cappelli, Ruben Ohana, Julien Launay, Laurent Meunier, Iacopo Poli, Florent Krzakala
2021 A* conf
Align, then memorise: the dynamics of learning with feedback alignment.
ICML
Maria Refinetti, Stéphane d'Ascoli, Ruben Ohana, Sebastian Goldt
2021 — conf
LightOn Optical Processing Unit : Scaling-up AI and HPC with a Non von Neumann co-processor.
HCS
Charles Brossollet, Alessandro Cappelli, Igor Carron, Charidimos Chaintoutis, Amélie Chatelain, Laurent Daudet, Sylvain Gigan, Daniel Hesslow, Florent Krzakala, Julien Launay, Safa Mokaadi, Fabien Moreau, Kilian Müller, Ruben Ohana, Gustave Pariente, Iacopo Poli, Giuseppe Luca Tommasone
2021 J jnl
LightOn Optical Processing Unit: Scaling-up AI and HPC with a Non von Neumann co-processor.
CoRR
Charles Brossollet, Alessandro Cappelli, Igor Carron, Charidimos Chaintoutis, Amélie Chatelain, Laurent Daudet, Sylvain Gigan, Daniel Hesslow, Florent Krzakala, Julien Launay, Safa Mokaadi, Fabien Moreau, Kilian Müller, Ruben Ohana, Gustave Pariente, Iacopo Poli, Giuseppe Luca Tommasone
2021 A* conf
Photonic Differential Privacy with Direct Feedback Alignment.
NeurIPS
Ruben Ohana, Hamlet Jesse Medina Ruiz, Julien Launay, Alessandro Cappelli, Iacopo Poli, Liva Ralaivola, Alain Rakotomamonjy
2021 J jnl
Photonic Differential Privacy with Direct Feedback Alignment.
CoRR
Ruben Ohana, Hamlet Jesse Medina Ruiz, Julien Launay, Alessandro Cappelli, Iacopo Poli, Liva Ralaivola, Alain Rakotomamonjy
2021 — conf
Photonic co-processors in HPC: Using LightOn OPUs for Randomized Numerical Linear Algebra.
HCS
Daniel Hesslow, Alessandro Cappelli, Igor Carron, Laurent Daudet, Raphaël Lafargue, Kilian Müller, Ruben Ohana, Gustave Pariente, Iacopo Poli
2021 J jnl
Photonic co-processors in HPC: using LightOn OPUs for Randomized Numerical Linear Algebra.
CoRR
Daniel Hesslow, Alessandro Cappelli, Igor Carron, Laurent Daudet, Raphaël Lafargue, Kilian Müller, Ruben Ohana, Gustave Pariente, Iacopo Poli
2021 J jnl
ROPUST: Improving Robustness through Fine-tuning with Photonic Processors and Synthetic Gradients.
CoRR
Alessandro Cappelli, Julien Launay, Laurent Meunier, Ruben Ohana, Iacopo Poli
2020 Misc conf
Kernel Computations from Large-Scale Random Features Obtained by Optical Processing Units.
ICASSP
Ruben Ohana, Jonas Wacker, Jonathan Dong, Sébastien Marmin, Florent Krzakala, Maurizio Filippone, Laurent Daudet
2020 A* conf
Reservoir Computing meets Recurrent Kernels and Structured Transforms.
NeurIPS
Jonathan Dong, Ruben Ohana, Mushegh Rafayelyan, Florent Krzakala
2020 J jnl
Reservoir Computing meets Recurrent Kernels and Structured Transforms.
CoRR
Jonathan Dong, Ruben Ohana, Mushegh Rafayelyan, Florent Krzakala
2020 J jnl
The dynamics of learning with feedback alignment.
CoRR
Maria Refinetti, Stéphane d'Ascoli, Ruben Ohana, Sebastian Goldt
2019 J jnl
Kernel computations from large-scale random features obtained by Optical Processing Units.
CoRR
Ruben Ohana, Jonas Wacker, Jonathan Dong, Sébastien Marmin, Florent Krzakala, Maurizio Filippone, Laurent Daudet