¡Hola!
I am a second-year Ph.D. student at Department of Electrical and Computer Engineering, Princeton University, advised by Prof. Jason M. Klusowski. Previously, I obtained B.Sc. in Computer Science with First Class Honours from the Chinese University of Hong Kong, with a minor in Mathematics.
I am interested in sampling and diffusion for language models. My current research explores relevant topics such as diffusion language models, discrete diffusion, statistical foundations of sampling methods, and connections to efficient reasoning abilities.
My hobbies include piano, soccer (football), photography, among others.
Publications
-
Decoding Game: On Minimax Optimality of Heuristic Text Generation Strategies.
Sijin Chen, Omar Hagrass, and Jason M. Klusowski,
International Conference on Learning Representations (ICLR), 2025. -
Escaping Saddle Points in Heterogeneous Federated Learning via Distributed SGD with Communication Compression.
Sijin Chen, Zhize Li, and Yuejie Chi,
International Conference on Artificial Intelligence and Statistics (AISTATS), 2024. -
Non-Convex Joint Community Detection and Group Synchronization via Generalized Power Method.
Sijin Chen, Xiwei Cheng, and Anthony Man-Cho So,
International Conference on Artificial Intelligence and Statistics (AISTATS), 2024. -
CIA-SSD: Confident IoU-Aware Single-Stage Object Detector from Point Cloud.
Wu Zheng, Weiliang Tang, Sijin Chen, Li Jiang, and Chi-Wing Fu,
AAAI Conference on Artificial Intelligence (AAAI), 2021.
Teaching
-
SML310: Research Projects in Data Science
Assistant in Instruction, 2024 Fall -
ORF570: Special Topics in Statistics and Operations Research: Transformers and Large Language Models
Assistant in Instruction, 2025 Spring
Awards
- Princeton University SEAS Travel Grant
- Gordon Y. S. Wu Fellowship in Engineering
- Hong Kong Government Scholarship for Outstanding Performance
- VTech Group of Companies Scholarship
Professional Service
- Reviewer: International Conference on Learning Representations (ICLR)
Curriculum Vitae
View the PDF version here.