37 skills found · Page 1 of 2
davda54 / SamSAM: Sharpness-Aware Minimization (PyTorch)
romilbert / SamformerOfficial implementation of SAMformer, a transformer leveraging Sharpness-Aware Minimization and Channel-Wise Attention for Time Series Forecasting.
moskomule / Sam.pytorchA PyTorch implementation of Sharpness-Aware Minimization for Efficiently Improving Generalization
val-iisc / SDAT[ICML 2022]Source code for "A Closer Look at Smoothness in Domain Adversarial Training",
sayakpaul / Sharpness Aware Minimization TensorFlowImplements sharpness-aware minimization (https://arxiv.org/abs/2010.01412) in TensorFlow 2.
Mi-Peng / Sparse Sharpness Aware Minimization[NeurIPS 2022] Make Sharpness-Aware Minimization Stronger: A Sparsified Perturbation Approach -- Official Implementation
Jannoshh / Simple SamSharpness-Aware Minimization for Efficiently Improving Generalization
tml-epfl / Understanding SamTowards Understanding Sharpness-Aware Minimization [ICML 2022]
rollovd / LookSAMThis is unofficial repository for Towards Efficient and Scalable Sharpness-Aware Minimization.
nblt / F SAM[CVPR 2024] Friendly Sharpness-Aware Minimization
tml-epfl / Sam Low Rank FeaturesSharpness-Aware Minimization Leads to Low-Rank Features [NeurIPS 2023]
JeanKaddour / WASAMWeight-Averaged Sharpness-Aware Minimization (NeurIPS 2022)
MediaBrain-SJTU / FedLESAM[ICML 2024 spotlight] This repository contains the implementation details for the paper "Locally Estimated Global Perturbations are Better than Local Perturbations for Federated Sharpness-aware Minimization"
WHU-ZQH / FSAM4PLM[EMNLP22] Improving Sharpness-Aware Minimization with Fisher Mask for Better Generalization on Language Models
OPTML-Group / Unlearn Smooth[ICML25] Official repo for "Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and Beyond"
zzpustc / CC SAMThis is the implementation of our CVPR'23 paper "Class-Conditional Sharpness-Aware Minimization for Deep Long-Tailed Recognition".
LOG-postech / SAM Overparam[UAI 2025] Official code for reproducing paper "Critical Influence of Overparameterization on Sharpness-aware Minimization"
CGCL-codes / TransferAttackSurrogatesThe official code of IEEE S&P 2024 paper "Why Does Little Robustness Help? A Further Step Towards Understanding Adversarial Transferability". We study how to train surrogates model for boosting transfer attack.
tranquyenbk173 / FHVI ICML2025FHBI: Improving Generalization with Flat Hilbert Bayesian Inference (ICML2025)
zzp1012 / SAM In Late Phase[ICLR 2025 Spotlight] Code release for "Sharpness-Aware Minimization Efficiently Selects Flatter Minima Late In Training"