A hypernetwork conditions a conservative-form CNN to predict WENO5 weights from mesh and initial-condition metadata, preserving conservation and generalizing across resolutions for 1D hyperbolic conservation laws.
International Conference on Learning Representations , year=
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
representative citing papers
LoRA adapters should be scaled by 1/sqrt(rank) rather than 1/rank to stabilize learning and enable effective use of higher ranks during fine-tuning of large language models.
Hyper-DFS uses hypernetworks and Set Transformers to generate on-demand parameters for feature subsets in dynamic selection, outperforming prior methods on tabular data and showing stronger zero-shot generalization.
citing papers explorer
-
Hypernetwork-Conditioned WENO5 Conservative-Form CNNs for One-Dimensional Conservation Laws
A hypernetwork conditions a conservative-form CNN to predict WENO5 weights from mesh and initial-condition metadata, preserving conservation and generalizing across resolutions for 1D hyperbolic conservation laws.
-
A Rank Stabilization Scaling Factor for Fine-Tuning with LoRA
LoRA adapters should be scaled by 1/sqrt(rank) rather than 1/rank to stabilize learning and enable effective use of higher ranks during fine-tuning of large language models.
-
Hypernetworks for Dynamic Feature Selection
Hyper-DFS uses hypernetworks and Set Transformers to generate on-demand parameters for feature subsets in dynamic selection, outperforming prior methods on tabular data and showing stronger zero-shot generalization.