I am a Ph.D. candidate in the Causal Artificial Intelligence Lab at Columbia University, working with Prof. Elias Bareinboim. I also work closely with Prof. Junzhe Zhang. Previously, during my Master’s studies at Brown University, I was fortunate enough to work with Prof. Michael Littman.
My research interest lies in the intersection of causal inference and reinforcement learning, especially in how to build a causally aligned, generalizable, and sample-efficient agent.
In the era of large language models, I believe a causally aligned agentic system is more important than ever. Beyond metric numbers, there are still many underexplored territories where classic problems like reward hacking, safety, alignment, and agent explainability/interpretability emerge again during RL post-training for LLM practitioners. My recent interest is in designing practical and scalable causal tools to mitigate those problems in language model training/testing.
Feel free to contact me if you are interested in working on causal reinforcement learning!
I’m also actively looking for Summer 2026 research internships!
Sept. 2025: Our paper 
![[poster]](https://icml.cc/media/PosterPDFs/ICML%202025/45757.png?t=1749957969.087192){kind=link}
![[poster]](/assets/papers/RLSSposter.png){kind=link}