| 2026 | ACL | POP: Prefill-Only Pruning for Efficient Large Model Inference. | Junhui He, Zhihui Fu, Jun Wang, Qingan Li |
| 2025 | ACL | A²ATS: Retrieval-Based KV Cache Reduction via Windowed Rotary Position Embedding and Query-Aware Vector Quantization. | Junhui He, Junna Xing, Nan Wang, Rui Xu, Shangyu Wu, Peng Zhou, Qiang Liu, Chun Jason Xue, Qingan Li |
| 2025 | DSN | Semantically Improved Adversarial Attack Based on Masked Language Model via Context Preservation. | Hao Tian, Hao-Tian Wu, Yiu-Ming Cheung, Junhui He, Zhihong Tian |
| 2025 | EMNLP | MLWQ: Efficient Small Language Model Deployment via Multi-Level Weight Quantization. | Chun Hu, Junhui He, Shangyu Wu, Yuxin He, Chun Jason Xue, Qingan Li |
| 2024 | EMNLP | CHESS: Optimizing LLM Inference via Channel-Wise Thresholding and Selective Sparsification. | Junhui He, Shangyu Wu, Weidong Wen, Chun Jason Xue, Qingan Li |
| 2009 | CIS | A CPK-Based Security Scheme at Network Layer. | Zhiyuan Xie, Junhui He, Shaohua Tang |
| 2005 | IWDW | A New Approach to Estimating Hidden Message Length in Stochastic Modulation Steganography. | Junhui He, Jiwu Huang, Guoping Qiu |