D'OH: Decoder-Only Random Hypernetworks for Implicit Neural Representations

C Gordon, LE MacDonald… - Proceedings of the …, 2024 - openaccess.thecvf.com
Deep implicit functions have been found to be an effective tool for efficiently encoding all
manner of natural signals. Their attractiveness stems from their ability to compactly represent …

Transfer Learning in Physics-Informed Neural Networks: Full Fine-Tuning, Lightweight Fine-Tuning, and Low-Rank Adaptation

Y Wang, J Bai, MS Eshaghi, C Anitescu… - arXiv preprint arXiv …, 2025 - arxiv.org
AI for PDEs has garnered significant attention, particularly Physics-Informed Neural
Networks (PINNs). However, PINNs are typically limited to solving specific problems, and …

Hyper-CL: Conditioning Sentence Representations with Hypernetworks

YH Yoo, J Cha, C Kim, T Kim - arXiv preprint arXiv:2403.09490, 2024 - arxiv.org
While the introduction of contrastive learning frameworks in sentence representation
learning has significantly contributed to advancements in the field, it still remains unclear …

Hyper Adversarial Tuning for Boosting Adversarial Robustness of Pretrained Large Vision Models

K Lv, H Cao, K Tu, Y Xu, Z Zhang, X Ding… - arXiv preprint arXiv …, 2024 - arxiv.org
Large vision models have been found vulnerable to adversarial examples, emphasizing the
need for enhancing their adversarial robustness. While adversarial training is an effective …

[PDF][PDF] M2 Internship: Mechanistic-Statistical Modeling with Physics-Informed Neural Networks

H Gangloff-hugo, N Jouvin-nicolas, P Gloaguen-pierre - mia-ps.inrae.fr
M2 Internship: Mechanistic-Statistical Modeling with Physics-Informed Neural Networks Page 1
M2 Internship: Mechanistic-Statistical Modeling with Physics-Informed Neural Networks …