24 citations · 90 across the 25 of their papers we have counts for
30 papers
CANTO: CAD-Native Transformer Operators for AI-Aided Engineering
Daniel Leibovici, Nikola Borislavov Kovachki, Dawon Ahn +8
Modern engineering systems, from automobiles to aircraft, are designed by using precise, continuous parametric computer-aided design (CAD) models. Evaluating design changes through…
On the Value of Tokeniser Pretraining in Physics Foundation Models
Hadi Sotoudeh, Payel Mukhopadhyay, Ruben Ohana +4
We investigate the impact of tokeniser pretraining on the accuracy and efficiency of physics emulation. Modern high-resolution simulations produce vast volumes of data spanning div…
Predicting partially observable dynamical systems via diffusion models with a multiscale inference scheme
Rudy Morel, Francesco Pio Ramunno, Jeff Shen +18
Conditional diffusion models provide a natural framework for probabilistic prediction of dynamical systems and have been successfully applied to fluid dynamics and weather predicti…
Universal Spectral Tokenization via Self-Supervised Panchromatic Representation Learning
Jeff Shen, Francois Lanusse, Liam Holden Parker +24
Sequential scientific data span many resolutions and domains, and unifying them into a common representation is a key step toward developing foundation models for the sciences. Ast…
Walrus: A Cross-Domain Foundation Model for Continuum Dynamics
Michael McCabe, Payel Mukhopadhyay, Tanya Marwah +22
Foundation models have transformed machine learning for language and vision, but achieving comparable impact in physical simulation remains a challenge. Data heterogeneity and unst…
AION-1: Omnimodal Foundation Model for Astronomical Sciences
Liam Parker, Francois Lanusse, Jeff Shen +24
While foundation models have shown promise across a variety of fields, astronomy still lacks a unified framework for joint modeling across its highly diverse data modalities. In th…
TC-LoRA: Temporally Modulated Conditional LoRA for Adaptive Diffusion Control
Minkyoung Cho, Ruben Ohana, Christian Jacobsen +4
Current controllable diffusion models typically rely on fixed architectures that modify intermediate activations to inject guidance conditioned on a new modality. This approach use…
Overtone: Cyclic Patch Modulation for Clean, Efficient, and Flexible Physics Emulators
Payel Mukhopadhyay, Michael McCabe, Ruben Ohana +1
Transformer-based PDE surrogates achieve remarkable performance but face two key challenges: fixed patch sizes cause systematic error accumulation at harmonic frequencies, and comp…
Lost in Latent Space: An Empirical Study of Latent Diffusion Models for Physics Emulation
François Rozet, Ruben Ohana, Michael McCabe +3
The steep computational cost of diffusion models at inference hinders their use as fast physics emulators. In the context of image and video generation, this computational drawback…
The Well: a Large-Scale Collection of Diverse Physics Simulations for Machine Learning
Ruben Ohana, Michael McCabe, Lucas Meyer +24
Machine learning based surrogate models offer researchers powerful tools for accelerating simulation-based workflows. However, as standard datasets in this space often cover small…
Streamlined optical training of large-scale modern deep learning architectures with direct feedback alignment
Ziao Wang, Kilian Müller, Matthew Filipovich +12
Modern deep learning relies nearly exclusively on dedicated electronic hardware accelerators. Photonic approaches, with low consumption and high operation speed, are increasingly c…
Contextual Counting: A Mechanistic Study of Transformers on a Quantitative Task
Siavash Golkar, Alberto Bietti, Mariel Pettee +12
Transformers have revolutionized machine learning across diverse domains, yet understanding their behavior remains crucial, particularly in high-stakes applications. This paper int…
Listening to the Noise: Blind Denoising with Gibbs Diffusion
David Heurtel-Depeiges, Charles C. Margossian, Ruben Ohana +1
In recent years, denoising problems have become intertwined with the development of deep generative models. In particular, diffusion models are trained like denoisers, and the dist…
Removing Dust from CMB Observations with Diffusion Models
David Heurtel-Depeiges, Blakesley Burkhart, Ruben Ohana +1
In cosmology, the quest for primordial -modes in cosmic microwave background (CMB) observations has highlighted the critical need for a refined model of the Galactic dust foregr…
Multiple Physics Pretraining for Physical Surrogate Models
Michael McCabe, Bruno Régaldo-Saint Blancard, Liam Holden Parker +11
We introduce multiple physics pretraining (MPP), an autoregressive task-agnostic pretraining approach for physical surrogate modeling of spatiotemporal systems with transformers. I…
xVal: A Continuous Numerical Tokenization for Scientific Language Models
Siavash Golkar, Mariel Pettee, Michael Eickenberg +11
Due in part to their discontinuous and discrete default encodings for numbers, Large Language Models (LLMs) have not yet been commonly used to process numerically-dense scientific…
Linear Optical Random Projections Without Holography
Ruben Ohana, Daniel Hesslow, Daniel Brunner +2
We introduce a novel method to perform linear optical random projections without the need for holography. Our method consists of a computationally trivial combination of multiple i…
MoMo: Momentum Models for Adaptive Learning Rates
Fabian Schaipp, Ruben Ohana, Michael Eickenberg +2
Training a modern machine learning architecture on a new task requires extensive learning-rate tuning, which comes at a high computational cost. Here we develop new Polyak-type ada…
Shedding a PAC-Bayesian Light on Adaptive Sliced-Wasserstein Distances
Ruben Ohana, Kimia Nadjahi, Alain Rakotomamonjy +1
The Sliced-Wasserstein distance (SW) is a computationally efficient and theoretically grounded alternative to the Wasserstein distance. Yet, the literature on its statistical prope…
Complex-to-Real Sketches for Tensor Products with Applications to the Polynomial Kernel
Jonas Wacker, Ruben Ohana, Maurizio Filippone
Randomized sketches of a tensor product of vectors follow a tradeoff between statistical efficiency and computational acceleration. Commonly used approaches avoid computing the…
LightOn Optical Processing Unit: Scaling-up AI and HPC with a Non von Neumann co-processor
Charles Brossollet, Alessandro Cappelli, Igor Carron +14
We introduce LightOn's Optical Processing Unit (OPU), the first photonic AI accelerator chip available on the market for at-scale Non von Neumann computations, reaching 1500 TeraOP…
ROPUST: Improving Robustness through Fine-tuning with Photonic Processors and Synthetic Gradients
Alessandro Cappelli, Julien Launay, Laurent Meunier +2
Robustness to adversarial attacks is typically obtained through expensive adversarial training with Projected Gradient Descent. Here we introduce ROPUST, a remarkably simple and ef…
Photonic Differential Privacy with Direct Feedback Alignment
Ruben Ohana, Hamlet J. Medina Ruiz, Julien Launay +4
Optical Processing Units (OPUs) -- low-power photonic chips dedicated to large scale random projections -- have been used in previous work to train deep neural networks using Direc…
Photonic co-processors in HPC: using LightOn OPUs for Randomized Numerical Linear Algebra
Daniel Hesslow, Alessandro Cappelli, Igor Carron +6
Randomized Numerical Linear Algebra (RandNLA) is a powerful class of methods, widely used in High Performance Computing (HPC). RandNLA provides approximate solutions to linear alge…