Junbiao Pang

works on

low-bit quantization 1 model tuning 1 post-training quantization 1 semantic segmentation 1 sgd optimization 1

From the 1 of 14 linked papers with an AI index.

activity

20242026

collaborators

Showing cs.CLShow all

1 paper · 1 filter

cs.CL2025

Efficiently Seeking Flat Minima for Better Generalization in Fine-Tuning Large Language Models and Beyond

Jiaxin Deng, Qingcheng Zhu, Junbiao Pang +3

Little research explores the correlation between the expressive ability and generalization ability of the low-rank adaptation (LoRA). Sharpness-Aware Minimization (SAM) improves mo…