collaborators

7 papers

cs.CV2025

Efficiently Training A Flat Neural Network Before It has been Quantizated

Peng Xia, Junbiao Pang, Tianyang Cai

Post-training quantization (PTQ) for vision transformers (ViTs) has garnered significant attention due to its efficiency in compressing models. However, existing methods typically…

cs.CV2025

Adaptively Sampling-Reusing-Mixing Decomposed Gradients to Speed Up Sharpness Aware Minimization

Jiaxin Deng, Junbiao Pang

Sharpness-Aware Minimization (SAM) improves model generalization but doubles the computational cost of Stochastic Gradient Descent (SGD) by requiring twice the gradient calculation…

cs.CV2025

MEC-Quant: Maximum Entropy Coding for Extremely Low Bit Quantization-Aware Training

Junbiao Pang, Tianyang Cai, Baochang Zhang

Quantization-Aware Training (QAT) has driven much attention to produce efficient neural networks. Current QAT still obtains inferior performances compared with the Full Precision (…

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…

cs.CV2025

Stabilizing Quantization-Aware Training by Implicit-Regularization on Hessian Matrix

Junbiao Pang, Tianyang Cai

Quantization-Aware Training (QAT) is one of the prevailing neural network compression solutions. However, its stability has been challenged for yielding deteriorating performances…

cs.LG2024

Unsupervised Abnormal Stop Detection for Long Distance Coaches with Low-Frequency GPS

Jiaxin Deng, Junbiao Pang, Jiayu Xu +1

In our urban life, long distance coaches supply a convenient yet economic approach to the transportation of the public. One notable problem is to discover the abnormal stop of the…