2025#
- 📄 Yongqi Leng, Yikun Lei, Xikai Liu, Meizhi Zhong, Bojian Xiong, Yurong Zhang, Yan Gao, Yao Hu, Deyi Xiong. DecEx-RAG: Boosting Agentic Retrieval-Augmented Generation with Decision and Execution Optimization via Process Supervision. EMNLP (2025) Industry.
- 📄 Bojian Xiong, Yikun Lei, Xikai Liu, Shaowei Zhang, Pengyun Zhu, Yan Liu, Yongqi Leng, Ling Shi, Meizhi Zhong, Yurong Zhang, Yan Gao, Yao Hu, Deyi Xiong. Think-Search-Patch: A Retrieval-Augmented Reasoning Framework for Repository-Level Code Repair. EMNLP (2025) Industry.
2024#
- 📄 Meizhi Zhong, Xikai Liu, Chen Zhang, Yikun Lei, Yan Gao, Yao Hu, Kehai Chen and Min Zhang. ZigZagKV: Dynamic KV Cache Compression for Long-context Modeling based on Layer Uncertainty. COLING(2025)
- 📄 Meizhi Zhong, Chen Zhang, Yikun Lei, Xikai Liu, Yan Gao, Yao Hu, Kehai Chen, Min Zhang. Understanding the RoPE Extensions of Long-Context LLMs: An Attention Perspective
. COLING(2025).
- 📄 Haoran Sun, Renren Jin, Shaoyang Xu, Leiyu Pan, Supryadi, Menglong Cui, Jiangcun Du, Yikun Lei, Lei Yang, Ling Shi, Juesi Xiao, Shaolin Zhu, Deyi Xiong. FuxiTranyu: A Multilingual Large Language Model Trained with Balanced Data. ArXiv(2024).
- 📄 Hao Wang, Zhengshan Xue, Yikun Lei, Deyi Xiong. End-to-End Speech Translation with Mutual Knowledge Distillation. ICASSP (2024).
- 📄 Xiaohu Zhao, Haoran Sun, Yikun Lei, Deyi Xiong. Regularizing Cross-Attention Learning for End-to-End Speech Translation with ASR and MT Attention Matrices. Expert Systems with Applications.
2023#
- 📄 Yikun Lei, Zhengshan Xue, Xiaohu Zhao, Haoran Sun, Shaolin Zhu, Xiaodong Lin, Deyi Xiong. CKDST: Comprehensively and Effectively Distill Knowledge from Machine Translation to End-to-End Speech Translation. ACL Findings(2023).
- 📄 Shaolin Zhu, Shangjie Li, Yikun Lei, Deyi Xiong. PEIT: Bridging the Modality Gap with Pre-trained Models for End-to-End Image Translation. ACL(2023).
- 📄 Haoran Sun, Xiaohu Zhao, Yikun Lei, Shaolin Zhu, Deyi Xiong. Towards a Deep Understanding of Multilingual End-to-End Speech Translation. EMNLP Findings(2023).
- 📄 Xiaohu Zhao, Haoran Sun, Yikun Lei, Shaolin Zhu, Deyi Xiong. CCSRD: Content-Centric Speech Representation Disentanglement Learning for End-to-End Speech Translation. EMNLP Findings(2023).
2022#