Research Interests
Iām interested in designing RL environments in which agents can genuinely learn. Designing a non-hackable environment is a lot like sculpting a work of art. As agents become more capable, the environments they require grow increasingly complex, and the distinction between a well-designed environment and a poorly designed one becomes ever more consequential. I am convinced that environments will become the most crucial component of post-training.
Previously, I worked on post-training LLMs for efficiency (reducing token and tool usage), safety (abstention), and general capability (math and question answering). Back then, I mainly designed rewards that shaped model behavior, along with tasks that probed how well those rewards worked.
š¬ If you have any feedbacks about me, enter it here.
Misc
At the end of my PhD, I started to explore more non-tech stuff to understand myself better, such as expressing more of my opinions and being more brave to show my imperfections in public, you can find my other social medias such as ē„ä¹, å°ēŗ¢ä¹¦, bilibili, å°å®å®.
š« Contact
Email: jinyansu6[@]gmail.com
Education
Experience
