collaborators

5 papers

cs.LG2026

ZO-Act: Efficient Zeroth-Order Fine-Tuning via One-Shot Activation-Informed Low-Rank Subspaces

Xun Dong, Yibo Xu, Naigang Wang +3

Zeroth-order (ZO) optimization enables fine-tuning large language models when backpropagation is unavailable or memory-prohibitive, but existing methods often perturb full model we…

cs.CV2026

Weight Group-wise Post-Training Quantization for Medical Foundation Model

Yineng Chen, Peng Huang, Aozhong Zhang +9

Foundation models have achieved remarkable results in medical image analysis. However, its large network architecture and high computational complexity significantly impact inferen…

cs.LG2026

DiaBlo: Diagonal Blocks Are Sufficient For Finetuning

Selcuk Gurses, Aozhong Zhang, Yanxia Deng +5

Fine-tuning is a critical step for adapting large language models (LLMs) to domain-specific downstream tasks. To mitigate the substantial computational and memory costs of full-mod…

cs.LG2024

COMQ: A Backpropagation-Free Algorithm for Post-Training Quantization

Aozhong Zhang, Zi Yang, Naigang Wang +4

Post-training quantization (PTQ) has emerged as a practical approach to compress large neural networks, making them highly efficient for deployment. However, effectively reducing t…

cs.LG2024

MagR: Weight Magnitude Reduction for Enhancing Post-Training Quantization

Aozhong Zhang, Naigang Wang, Yanxia Deng +3

In this paper, we present a simple optimization-based preprocessing technique called Weight Magnitude Reduction (MagR) to improve the performance of post-training quantization. For…