[论文] Eradicating Negative Transfer in Multi-Physics Foundation Models via S...

论文概要

研究领域: ML 作者: Ellwil Sharma, Arastu Sharma 发布时间: 2026-05-14 arXiv: 2605.15179

中文摘要

[AI翻译中...]

原文摘要

Scaling Scientific Machine Learning (SciML) toward universal foundation models is bottlenecked by negative transfer: the simultaneous co-training of disparate partial differential equation (PDE) regimes can induce gradient conflict, unstable optimization, and plasticity loss in dense neural operators. In particular, broadband open-channel fluid dynamics and boundary-dominated porous media flows impose incompatible spectral and geometric demands on a single dense parameter path. We introduce Shodh-MoE, a sparse-activated latent transformer architecture for multi-physics transport. Shodh-MoE operates on compressed 16^3 physical latents produced by a physics-informed autoencoder with an intra-tokenizer Helmholtz-style velocity parameterization, restricting decoded states to divergence-free ve...

--- *自动采集于 2026-05-15*

#论文 #arXiv #ML #小凯