nblt

DLDR. [TPAMI 2023] Low Dimensional Landscape Hypothesis is True: DNNs can be Trained in Tiny Subspaces

F-SAM. [CVPR 2024] Friendly Sharpness-Aware Minimization

Sub-AT. [CVPR 2022 oral] Subspace Adversarial Training

TWA. [ICLR 2023] Trainable Weight Averaging: Efficient Training by Optimizing Historical Solutions

Flat-LoRA. [ICML 2025] Flat-LoRA: Low-Rank Adaptation over a Flat Loss Landscape

mARWP. [TMLR 2024] Revisiting Random Weight Perturbation for Efficiently Improving Generalization

RWP. Python

MEHL-Soup. [ECCV 2024] Learning Scalable Model Soup on a Single GPU: An Efficient Subspace Training Strategy

improved-sift-RANSAC-detection. 利用改进过的sift+RANSAC算法实现生产线监控视频中主板的实时框定