Zhipeng Jia — accepted AI-conference papers

2025

Spark Transformer: Reactivating Sparsity in Transformer FFN and Attention

Chong You, Kan Wu, Zhipeng Jia, Lin Chen, Srinadh Bhojanapalli, Jiaxian Guo +13

NeurIPS 2025poster

The discovery of the *lazy neuron phenomenon* (Li et al., 2022), where fewer than 10% of the feedforward networks (FFN) parameters in trained Transformers are activated per token, has spurred significant interests in *activation sparsity* for enhancing large model efficiency. While notable progress…

Cited by 0 Source ↗Scholar ↗

2015

Deep convolutional activation features for large scale Brain Tumor histopathology image classification and segmentation

Yan Xu, Zhipeng Jia, Yuqing Ai, Fang Zhang, Maode Lai, Eric I-Chao Chang

ICASSP 2015accepted

We propose a simple, efficient and effective method using deep convolutional activation features (CNNs) to achieve stat- of-the-art classification and segmentation for the MICCAI 2014 Brain Tumor Digital Pathology Challenge. Common traits of such medical image challenges are characterized by large i…

Cited by 0 Source ↗Scholar ↗