Junyan Cheng
About Me
I am a third-year Ph.D. candidate at Dartmouth College, fully funded by PhD Innovation Fellowship (Thayer & Tuck collaborative, hosted by Dr. Eric R. Fossum). I am currently a research intern at Microsoft Research Redmond, working with Dr. Jay Stokes, on autonomous software engineering. I interned for 6 months at the Allen Institute for AI (Ai2) under Dr. Kyle Richardson on autonomous scientific discovery.
About My Research
- Goal: Autonomous Complex Problem-Solving, build intelligent systems that can stably, trustworthily, and scalably handle complex real-world scenarios in long-term large-scale deployments.
- Approach: Neural-Symbolic Program Synthesis, I combine the powerful LLM-agentic synthesizers with symbolic approaches, including logic, programming language, and optimization methods.
- Applications: I am especially interested in Financial Economics, Software Engineering, Scientific Discovery, and Robotics.
I seriously care about how AI can make a fairer, happier, Pareto-efficient society, as it is not simply a problem of better automation or higher productivity.
Publications
-
arXiv
-
FinAI@ICLR
ICLR 2025 Advances in Financial AI Workshop (Long Paper track), 2025. -
ICLR
International Conference on Learning Representations (ICLR), 2024. -
ICLR
International Conference on Learning Representations (ICLR), 2024. -
JCISE
Journal of Computing and Information Science in Engineering -
EMNLP
Conference on Empirical Methods in Natural Language Processing (EMNLP Long Paper), 2021. -
arXiv
arXiv preprint, arXiv:2112.00663 -
arXiv
arXiv preprint, arXiv:2111.08874 -
RNA biology
RNA biology, 2018, VOL. 15, NO. 9, 1192-1205
Powered by Jekyll and Minimal Light theme.