3 papers
cs.LG2025
Data-Free Quantization via Mixed-Precision Compensation without Fine-Tuning
Jun Chen, Shipeng Bai, Tianxin Huang +3
Neural network quantization is a very promising solution in the field of model compression, but its resulting accuracy highly depends on a training/fine-tuning process and requires…
cs.LG2025
Hyperbolic Binary Neural Network
Jun Chen, Jingyang Xiang, Tianxin Huang +2
Binary Neural Network (BNN) converts full-precision weights and activations into their extreme 1-bit counterparts, making it particularly suitable for deployment on lightweight mob…
cs.LG2024
Learning Discretized Neural Networks under Ricci Flow
Jun Chen, Hanwen Chen, Mengmeng Wang +3
In this paper, we study Discretized Neural Networks (DNNs) composed of low-precision weights and activations, which suffer from either infinite or zero gradients due to the non-dif…