I am a Member of Technical Staff at Anthropic. I am also a Ph.D. student at the University of Texas at Austin, advised by Prof. Zhangyang Wang. Prior to that, I received my M.S. and B.S. degrees from Shanghai Jiao Tong University (SJTU) in 2023 and 2020, respectively.
My current research interests lie in LLM Interpretability, safety and alignment. If you’re interested in my work, feel free to contact me.
🔥 News
- 2023.06: 🎉🎉 I’m going to join VITA in August, 2023!
- 2025.03: 🎉🎉 I’m going to join Anthropic as a AI safety Research Fellow!
- 2025.10: 🎉🎉 I have joined Anthropic full-time as a Member of Technical Staff!
📝 Selected Publications
Persona Vectors: Monitoring and Controlling Character Traits in Language Models
Runjin Chen, Andy Arditi, Henry Sleight, Owain Evans, Jack Lindsey
SEAL: Steerable Reasoning Calibration of Large Language Models for Free [COLM 2025]
Runjin Chen*, Zhenyu Zhang*, Junyuan Hong, Souvik Kundu, Zhangyang Wang
LLaGA: Large Language and Graph Assistant [ICML 2024]
Runjin Chen, Tong Zhao, Ajay Jaiswal, Neil Shah, Zhangyang Wang
Extracting and Understanding the Superficial Knowledge in Alignment [NAACL 2025]
Runjin Chen, Gabriel Jacob Perin, Xuxi Chen, Xilun Chen, Yan Han, Nina S. T. Hirata , Junyuan Hong, Bhavya Kailkhura
Enhancing Item Tokenization for Generative Recommendation through Self-Improvement
Runjin Chen, Mingxuan Ju, Ngoc Bui, Dimosthenis Antypas, Stanley Cai, Xiaopeng Wu, Leonardo Neves, Zhangyang Wang, Neil Shah, Tong Zhao
Q-Hitter: A Better Token Oracle for Efficient LLM Inference via Sparse-Quantized KV Cache [MLSys 2024]
Zhenyu Zhang, Shiwei Liu, Runjin Chen, Bhavya Kailkhura, Beidi Chen, Zhangyang Wang
Found in the Middle: How Language Models Use Long Contexts Better via Plug-and-Play Positional Encoding [Neurips 2024]
Zhenyu Zhang, Runjin Chen, Shiwei Liu, Zhewei Yao, Olatunji Ruwase, Beidi Chen, Xiaoxia Wu, Zhangyang Wang
GCF-RD: A Graph-based Contrastive Framework for Semi-Supervised Learning on Relational Databases [CIKM 2022]
Runjin Chen, Tong Li, Yanyan Shen, Luyu Qiu, Kaidi Li, Caleb Chen Cao
GNEM: A Generic One-to-Set Neural Entity Matching [WWW 2021]
Runjin Chen, Yanyan Shen, Dongxiang Zhang
Explaining Neural Networks Semantically and Quantitatively [ICCV 2019 oral]
Runjin Chen*, Hao Chen*, Jie Ren, Ge Huang, Quanshi Zhang
Towards a Deep and Unified Understanding of Deep Neural Models in NLP [ICML 2019]
Chaoyu Guan*, Xiting Wang*, Quanshi Zhang, Runjin Chen, Di He, Xing Xie
📖 Educations
- 2023 - 2028(expected), PHD in Electrical and Computer Engineering, University of Texas at Austin.
- 2020 - 2023, Master in Computer Science, Shanghai Jiao Tong University.
- 2016 - 2020, Bachelor in Computer Science, Shanghai Jiao Tong University.
💻 Working Experience
-
2025.10 - present, Member of Technical Staff at Anthropic.
-
2025.03 - 2025.09, Reasearch Fellow at Anthropic, Berkeley.
-
2024.06 - 2024.10, Reasearch Intern at Snap, Bellevue.
-
2023.02 - 2023.06, MLE at Bytedance, Shanghai.
🎖 Honors and Awards
- 2023.03 Outstanding Graduate Student of Shanghai Jiao Tong University.
- 2021.07 Yangyuanqin Scholarship.
- 2020.06 Zhiyuan Honor Degree of Bachelor of Engineering.
- 2018.11 The First Prize in Contemporary Undergraduate Mathematical Contest in Modeling.
- 2018.03 Meritorious Prize in Mathematical Contest in Modeling.
- 2017.11 National Scholarship Award (top1% in SJTU).