Showing cs.LGShow all
3 papers · 1 filter
cs.LG2026
Out-of-distribution transfer of PDE foundation models to material dynamics under extreme loading
Mahindra Rautela, Alexander Most, Siddharth Mansingh +9
Most PDE foundation models are pretrained and fine-tuned on fluid-centric benchmarks. Their utility under extreme-loading material dynamics remains unclear. We benchmark out-of-dis…
cs.LG2025
Towards Reasoning for PDE Foundation Models: A Reward-Model-Driven Inference-Time-Scaling Algorithm
Siddharth Mansingh, James Amarel, Ragib Arnab +10
Partial Differential Equations (PDEs) are the bedrock for modern computational sciences and engineering, and inherently computationally expensive. While PDE foundation models have…
cs.LG2024
How Robust Are Energy-Based Models Trained With Equilibrium Propagation?
Siddharth Mansingh, Michal Kucer, Garrett Kenyon +2
Deep neural networks (DNNs) are easily fooled by adversarial perturbations that are imperceptible to humans. Adversarial training, a process where adversarial examples are added to…