Junyan Cheng
About Me
I am a fourth-year Ph.D. candidate at Dartmouth College, advised by Prof. Peter Chin at LISP Lab, fully funded by PhD Innovation Fellowship (Thayer & Tuck collaborative, hosted by Prof. Eric R. Fossum). I interned in the AIIL Group at Microsoft Research Redmond, mentored by Dr. Jay Stokes, on autonomous software engineering, and 6 months at the Allen Institute for AI (Ai2) under Dr. Kyle Richardson on autonomous scientific discovery.
About My Research
I built complex LLM-agentic systems across autonomous scientific discovery, societal systems, and software engineering (mostly driven by the š§LLLM framework I developed, feel free to try!). In particular, I developed a web app š§ Analytica (Research Preview Demo) for LLM-agentic analysis. Check live demos of my flagship systems below (click to explore):
Analytica
Robust and efficient wide and deep LLM-agentic analysis and forecasting with soft logic and parallel Jupyter Notebook analysts.
Genesys
Distributed discovery system for novel language model architectures with autonomous design and evaluation.
Apeiron
Scalable and autonomous full-lifecycle demand-optimized app synthesizer with multi-thread CUA evaluators.
SocioDojo
LLM agentic lifelong societal modeling and analysis with news feed and real-time data flow. A "Human World Model".
My goal is to achieve autonomous systems that can accurately, reliably, and efficiently take over critical real-world domains in long-term large-scale deployments, with a holographic perception of the world dynamics (e.g., world models). I focus on Hybrid and Neural-symbolic AI that enhances powerful NNs and LLMs with symbolic approaches, such as logic, statistics, programming, and optimization (why we still need symbols? itās like why we still need laws, not only education!).
Publications
-
NeurIPS
The Thirty-ninth Annual Conference on Neural Information Processing Systems (NeurIPS), 2025. -
FinAI@ICLR
ICLR 2025 Advances in Financial AI Workshop (Long Paper track), 2025. -
ICLR
The Twelfth International Conference on Learning Representations (ICLR), 2024. -
ICLR
The Twelfth 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 Main), 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.