AIConfPaper
← Search

Francois Lanusse

9 accepted papers

2026

Walrus: A Cross-domain Foundation Model for Continuum Dynamics

Michael McCabe, Payel Mukhopadhyay, Tanya Marwah, Bruno Régaldo-Saint Blancard, François Rozet, Cristiana Diaconu +19
ICML 2026spotlight

Foundation models have transformed machine learning for language and vision, but achieving comparable impact in physical simulation remains a challenge. Data heterogeneity and unstable long-term dynamics inhibit learning from sufficiently diverse dynamics, while varying resolutions and dimensionalit…

Cited by 0Source ↗Scholar ↗
2025

AION-1: Omnimodal Foundation Model for Astronomical Sciences

Liam Holden Parker, Francois Lanusse, Jeff Shen, Ollie Liu, Tom Hehir, Leopoldo Sarra +19
NeurIPS 2025poster

While foundation models have shown promise across a variety of fields, astronomy lacks a unified framework for joint modeling across its highly diverse data modalities. In this paper, we present AION-1, the first large-scale multimodal foundation family of models for astronomy. AION-1 enables arbitr…

Cited by 0Source ↗Scholar ↗
2025

Lost in Latent Space: An Empirical Study of Latent Diffusion Models for Physics Emulation

François Rozet, Ruben Ohana, Michael McCabe, Gilles Louppe, Francois Lanusse, Shirley Ho
NeurIPS 2025poster

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 has been addressed by generating in the latent space of an autoencoder instead of the pixel space. In this work, we inv…

Cited by 0Source ↗code ↗Scholar ↗
2025

Predicting partially observable dynamical systems via diffusion models with a multiscale inference scheme

Rudy Morel, Francesco Pio Ramunno, Jeff Shen, Alberto Bietti, Kyunghyun Cho, Miles Cranmer +15
NeurIPS 2025poster

Conditional diffusion models provide a natural framework for probabilistic prediction of dynamical systems and have been successfully applied to fluid dynamics and weather prediction. However, in many settings, the available information at a given time represents only a small fraction of what is nee…

Cited by 0Source ↗Scholar ↗
2024

Learning Diffusion Priors from Observations by Expectation Maximization

François Rozet, Gérôme Andry, Francois Lanusse, Gilles Louppe
NeurIPS 2024poster

Diffusion models recently proved to be remarkable priors for Bayesian inverse problems. However, training these models typically requires access to large amounts of clean data, which could prove difficult in some settings. In this work, we present a novel method based on the expectation-maximization…

Cited by 15Source ↗PDF ↗Scholar ↗
2024

Multiple Physics Pretraining for Spatiotemporal Surrogate Models

Michael McCabe, Bruno Régaldo-Saint Blancard, Liam Holden Parker, Ruben Ohana, Miles Cranmer, Alberto Bietti +8
NeurIPS 2024poster

We introduce multiple physics pretraining (MPP), an autoregressive task-agnostic pretraining approach for physical surrogate modeling of spatiotemporal systems with transformers. In MPP, rather than training one model on a specific physical system, we train a backbone model to predict the dynamics o…

Cited by 3Source ↗PDF ↗Scholar ↗
2024

The Multimodal Universe: Enabling Large-Scale Machine Learning with 100 TB of Astronomical Scientific Data

Eirini Angeloudi, Jeroen Audenaert, Micah Bowles, Benjamin M. Boyd, David Chemaly, Brian Cherinka +23
NeurIPS 2024poster

We present the `Multimodal Universe`, a large-scale multimodal dataset of scientific astronomical data, compiled specifically to facilitate machine learning research. Overall, our dataset contains hundreds of millions of astronomical observations, constituting 100TB of multi-channel and hyper-spectr…

Cited by 2Source ↗PDF ↗code ↗Scholar ↗
2024

Unified Framework for Diffusion Generative Models in SO(3): Applications in Computer Vision and Astrophysics

Yesukhei Jagvaral, Francois Lanusse, Rachel Mandelbaum
AAAI 2024technical

Diffusion-based generative models represent the current state-of-the-art for image generation. However, standard diffusion models are based on Euclidean geometry and do not translate directly to manifold-valued data. In this work, we develop extensions of both score-based generative models (SGMs) an…

Cited by 8Source ↗PDF ↗Scholar ↗
2021

Adaptive wavelet distillation from neural networks through interpretations

Wooseok Ha, Chandan Singh, Francois Lanusse, Srigokul Upadhyayula, Bin Yu
NeurIPS 2021poster

Recent deep-learning models have achieved impressive prediction performance, but often sacrifice interpretability and computational efficiency. Interpretability is crucial in many disciplines, such as science and medicine, where models must be carefully vetted or where interpretation is the goal its…

Cited by 51Source ↗PDF ↗Scholar ↗