About
Chenlong Deng is a fourth-year PhD student at the Gaoling School of Artificial Intelligence, Renmin University of China, advised by Prof. Zhicheng Dou. He received his Bachelor's degree in Computer Science from Renmin University of China in 2022.
His research lies at the intersection of Large Language Models (LLMs) and Information Retrieval (IR), with a current focus on two directions:
- Efficient Long-Context Language Models: exploring sparsity and compression techniques to enable LLMs to process extended contexts efficiently.
- Deep Search Agents: investigating LLM-based agentic systems for complex, multi-step information seeking.
His work is grounded in years of research experience in information retrieval, spanning both fundamental and applied topics.
He is actively seeking research internship and full-time opportunities. Feel free to reach out if you are interested in collaboration.
Education & Experience
Education
Renmin University of China
PhD in Artificial Intelligence
Beijing, China
2022 - PresentRenmin University of China
B.Eng. in Computer Science
Beijing, China
2018 - 2022Experience
ByteDance Seed
Research Intern
Beijing, China
Apr 2026 - PresentMultimodal foundation models
Tencent AI Lab
Research Intern
Shenzhen, China
Apr 2024 - Jul 2025Efficient long-context LLMs
Education
Renmin University of China
PhD in Artificial Intelligence
Beijing, China
2022 - PresentRenmin University of China
B.Eng. in Computer Science
Beijing, China
2018 - 2022Experience
ByteDance Seed
Multimodal foundation models
Research Intern
Beijing, China
Apr 2026 - PresentTencent AI Lab
Efficient long-context LLMs
Research Intern
Shenzhen, China
Apr 2024 - Jul 2025News
We released DeepImageSearch, defining a new paradigm for image retrieval.
1 paper accepted to NeurIPS 2025 🎉 Thanks to all collaborators!
2 papers accepted to ACL 2025, including 1 Oral 🎉 Thanks to all collaborators!
4 papers accepted to EMNLP 2024 🎉 Thanks to all collaborators!
Selected Publications
View All→
UniGist: Towards General and Hardware-Aligned Sequence-Level Long Context Compression
Chenlong Deng, Zhisong Zhang, Kelong Mao, Shuaiyi Li, Tianqing Fang, Hongming Zhang, Haitao Mi, Dong Yu, Zhicheng Dou
