IEEE TNNLS

Efficient Tuning Before Low-Bit Post-Training Quantization for Stochastic Gradient Descent-optimized Models

用于随机梯度下降优化模型的低位后训练量化前的高效调优

Peng Xia, Junbiao Pang, Muhammad Ayub Sabir

机构 * School of Information Science and Technology, Beijing University of Technology（北京工业大学信息科学与技术学院） 纠错

AI总结 研究针对低位后训练量化性能易降问题，提出ETBQ方法，在随机梯度下降优化模型的PTQ前进行预处理调优，通过从量化误差分布采样扰动优化全精度模型，实验证明该方法能提升不同任务的低位PTQ性能。

Comments v2 revision: Added hyperparameter settings of all experiments in appendix, fixed minor typos, adjusted figure layout, polished experimental analysis. 12 pages, 10 figures, submitted to IEEE Transactions on Neural Networks and Learning Systems (TNNLS). Code available at https://github.com/xpxpxp2001xpxpxp/ETBQ

PMSN: A Parallel Multi-compartment Spiking Neuron for Multi-scale Temporal Processing

PMSN：一种用于多尺度时间处理的并行多房室脉冲神经元

Xinyi Chen, Jibin Wu, Chenxiang Ma, Yinsong Yan, Hanwen Liu, Yujie Wu, Kay Chen Tan

AI总结 研究针对脉冲神经网络多尺度时间处理不足问题，提出并行多房室脉冲神经元模型PMSN，通过整合子结构模拟生物神经元，引入并行化技术，实验表明其在时间处理能力和训练速度上优于现有模型，在神经形态硬件上可部署。

Journal ref IEEE Transactions on Neural Networks and Learning Systems, 2026