Xiangchen Song (宋祥辰)
I am a PhD student in Machine Learning Department at Carnegie Mellon University, advised by Prof. Kun Zhang (CMU-CLeaR Group). Previously, I studied Computer Science at UIUC with Prof. Jiawei Han.
research
Large language models are sequence models, and my work aims to make their internal representations provably identifiable so we can interpret and steer model behavior with principled guarantees. I build on causal representation learning to recover latent structure in temporal data (time series, video, and text), and bring this lens to mechanistic interpretability of LLMs: designing identifiable sparse autoencoders (SAEs) with feature consistency for LLM activations, analyzing internal reasoning mechanisms, and enabling targeted control for more reliable and efficient model behavior.
contact
Email: xiangchs [at] cs [dot] cmu [dot] edu
news
| May 13, 2026 | I am happy to be recognized as a Gold Reviewer for ICML 2026. I hope our efforts can contribute to a better peer-review process in the community!! |
|---|---|
| May 01, 2026 | One paper on LLM Agent benchmark and one paper on modular LLM reasoning have been accepted to Forty-third International Conference on Machine Learning (ICML’2026)!! |
| Apr 08, 2026 | I received a Modal for Academics compute grant to support my research on LLM test-time training. Many thanks to Modal for their generous support! |
| Apr 06, 2026 | One paper on mechanistic interpretability and one paper on diffusion large language models have been accepted to The 64th Annual Meeting of the Association for Computational Linguistics (ACL’2026)!! |
| Sep 23, 2025 | Two papers about efficient LLM reasoning have been accepted to NeurIPS 2025 Workshop on Efficient Reasoning (ER@NeurIPS’2025)!! |