← Search

Hanyu HU

2 accepted papers

2026

Taming the Loss Landscape of PINNs with Noisy Feynman–Kac Supervision: Operator Preconditioning and Non-Asymptotic Error Bounds

ICML 2026poster

Physics-Informed Neural Networks (PINNs) often train slowly or fail to converge on challenging partial differential equations (PDEs), a behavior recently linked to severely ill-conditioned loss landscapes inherited from the underlying differential operator. We propose FK-PINNs, a simple modification…

Cited by 0SourceScholar
2025

FISTAPruner: Layer-wise Post-training Pruning for Large Language Models

EMNLP 2025

Pruning is a critical strategy for compressing trained large language models (LLMs), aiming at substantial memory conservation and computational acceleration without compromising performance. However, existing pruning methods typically necessitate inefficient retraining for billion-scale LLMs or rel

Cited by 0SourcePDFScholar