Siddhartha Mishra

Full Professor@Swiss Federal Institute of Technology·瑞士·OpenReview

研究方向

Graph representation learning · Operator Learning · Sequence modeling · Deep Learning for Physics · Deep Learning · Computational Fluid dynamics · Computational Physics · Numerical methods for PDEs

5.3

HyPINO: Multi-Physics Neural Operators via HyperPINNs and the Method of Manufactured Solutions

NeurIPS 2025Spotlight

7.3

Geometry Aware Operator Transformer as an efficient and accurate neural surrogate for PDEs on arbitrary domains

NeurIPS 2025Poster

通讯

6.8

RIGNO: A Graph-based Framework For Robust And Accurate Operator Learning For PDEs On Arbitrary Domains

NeurIPS 2025Poster

通讯

3.5

S7: Selective and Simplified State Space Layers for Sequence Modeling

合作者 (20)

Siddhartha Mishra

Towards a Certificate of Trust: Task-Aware OOD Detection for Scientific AI

Rectified Flows for Fast Multiscale Fluid Flow Modeling

Neuro-Symbolic AI for Analytical Solutions of Differential Equations

HyPINO: Multi-Physics Neural Operators via HyperPINNs and the Method of Manufactured Solutions

Geometry Aware Operator Transformer as an efficient and accurate neural surrogate for PDEs on arbitrary domains

RIGNO: A Graph-based Framework For Robust And Accurate Operator Learning For PDEs On Arbitrary Domains

S7: Selective and Simplified State Space Layers for Sequence Modeling