Zobrazeno 1 - 10
of 604
pro vyhledávání: '"MISHRA, SIDDHARTHA"'
A central challenge in sequence modeling is efficiently handling tasks with extended contexts. While recent state-space models (SSMs) have made significant progress in this area, they often lack input-dependent filtering or require substantial increa
Externí odkaz:
http://arxiv.org/abs/2410.03464
Autor:
Molinaro, Roberto, Lanthaler, Samuel, Raonić, Bogdan, Rohner, Tobias, Armegioiu, Victor, Wan, Zhong Yi, Sha, Fei, Mishra, Siddhartha, Zepeda-Núñez, Leonardo
We present a generative AI algorithm for addressing the challenging task of fast, accurate and robust statistical computation of three-dimensional turbulent fluid flows. Our algorithm, termed as GenCFD, is based on a conditional score-based diffusion
Externí odkaz:
http://arxiv.org/abs/2409.18359
Autor:
Herde, Maximilian, Raonić, Bogdan, Rohner, Tobias, Käppeli, Roger, Molinaro, Roberto, de Bézenac, Emmanuel, Mishra, Siddhartha
We introduce Poseidon, a foundation model for learning the solution operators of PDEs. It is based on a multiscale operator transformer, with time-conditioned layer norms that enable continuous-in-time evaluations. A novel training strategy leveragin
Externí odkaz:
http://arxiv.org/abs/2405.19101
The joint prediction of continuous fields and statistical estimation of the underlying discrete parameters is a common problem for many physical systems, governed by PDEs. Hitherto, it has been separately addressed by employing operator learning surr
Externí odkaz:
http://arxiv.org/abs/2405.14558
Despite the effectiveness of data selection for large language models (LLMs) during pretraining and instruction fine-tuning phases, improving data efficiency in supervised fine-tuning (SFT) for specialized domains poses significant challenges due to
Externí odkaz:
http://arxiv.org/abs/2403.07384
Autor:
De Ryck, Tim, Mishra, Siddhartha
Publikováno v:
Acta Numerica 33 (2024) 633-713
Physics-informed neural networks (PINNs) and their variants have been very popular in recent years as algorithms for the numerical simulation of both forward and inverse problems for partial differential equations. This article aims to provide a comp
Externí odkaz:
http://arxiv.org/abs/2402.10926
The automated discovery of constitutive laws forms an emerging research area, that focuses on automatically obtaining symbolic expressions describing the constitutive behavior of solid materials from experimental data. Existing symbolic/sparse regres
Externí odkaz:
http://arxiv.org/abs/2402.04263
Autor:
Rohner, Tobias, Mishra, Siddhartha
This work presents the development, performance analysis and subsequent optimization of a GPU-based spectral hyperviscosity solver for turbulent flows described by the three dimensional incompressible Navier-Stokes equations. The method solves for th
Externí odkaz:
http://arxiv.org/abs/2401.09843
Autor:
Scellier, Benjamin, Mishra, Siddhartha
Resistor networks have recently attracted interest as analog computing platforms for machine learning, particularly due to their compatibility with the Equilibrium Propagation training framework. In this work, we explore the computational capabilitie
Externí odkaz:
http://arxiv.org/abs/2312.15063