I am Yuanteng Chen (陈远腾), a 24-year-old Ph.D. student at the Institute of Automation, Chinese Academy of Sciences (CASIA) and Zhongguancun Academy, advised by Prof. Jian Cheng. I graduated from the University of Chinese Academy of Sciences (UCAS), majoring in Computer Science and Technology. My research focuses on efficient large language models, especially model compression and inference acceleration for modern LLMs and MoE architectures. 🪨 爱好下围棋，业余6段，野狐围棋ID“月光底下走”，欢迎来找我下棋！
|
Post-training quantization, low-bit inference, pruning, and expert pruning for MoE models. |
Hardware-aware and system-aware acceleration for practical LLM deployment. |
Routing / Expert Selection with human intervention, routing adjustment, and inference enhancement. |
I am particularly interested in making MoE models more efficient, adaptive, and practical for real-world deployment. Always looking forward to exchanging ideas around LLM compression, MoE inference, and efficient AI systems!
- [2026.08.21] 🎉 Two papers accepted by EMNLP 2026: MODE to the Main Conference, and Ban&Pick to Findings.
- [2026.05.01] 🎉 Certain Head, Uncertain Tail: Expert-Sample for Test-Time Scaling in Fine-Grained MoE has been accepted by ICML 2026.
|
Yuanteng Chen, Peisong Wang, Zhilei Liu, Nanxin Zeng, Yuantian Shao, Shiqiang Lang, Tao Liu, Chuangyi Li, Qinghao Hu, Gang Li, Jing Liu, Jian Cheng Conference on Empirical Methods in Natural Language Processing (EMNLP 2026 Main)
|
|
Yuanteng Chen, Peisong Wang, Yuantian Shao, Nanxin Zeng, Chang Xu, Jian Cheng Findings of the Conference on Empirical Methods in Natural Language Processing (EMNLP 2026 Findings)
|
|
Yuanteng Chen, Peisong Wang, Nanxin Zeng, Yuantian Shao, Gang Li, Jing Liu, Jian Cheng International Conference on Machine Learning (ICML 2026)
|
|
Yuantian Shao, Peisong Wang, Yuanteng Chen, Chang Xu, Zhihui Wei, Jian Cheng International Conference on Machine Learning (ICML 2026)
|
|
Yuanteng Chen*, Yuantian Shao*, Peisong Wang, Jian Cheng Annual Meeting of the Association for Computational Linguistics (ACL 2025 Main)
|
|
Chen Tianqi*, Yuanteng Chen*, Peisong Wang, Weixiang Xu, Zeyu Zhu, Jian Cheng Findings of the Association for Computational Linguistics (ACL 2025 Findings)
|
|
Yuantian Shao*, Yuanteng Chen*, Peisong Wang, Jianlin Yu, Jing Lin, Yiwu Yao, Zhihui Wei, Jian Cheng Advances in Neural Information Processing Systems (NeurIPS 2025)
|
