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 (NSF Research Traineeship under Prof. Eric R. Fossum, Thayer School of Engineering & Tuck School of Business collaborative). I interned in the AIIL Group at Microsoft Research Redmond, mentored by Dr. Jay Stokes on software development agents, and 6 months at the Allen Institute for AI (Ai2) under Dr. Kyle Richardson on autonomous scientific discovery.
About My Research
My research spans the NLP and DL stack, from representation learning (ICLR’24), multimodal Transformer architecture (EMNLP’21), automatic pre-training and architecture discovery (NeurIPS’25 Spotlight), to agentic systems for society (ICLR’24 Spotlight) and finance (FinAI@ICLR’25). I pursue the AI that can accurately, reliably, and efficiently operate in high-stakes domains (e.g., science, finance, robotics) where the cost of a mistake is high, in long-term, large-scale deployments, with a holographic perception of the complex world (e.g., world models). I’m interested in Neural-symbolic and Evolutionary AI that draws on ideas from logic, probability, and program synthesis to achieve this.
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".
I have built multiple complex LLM-agentic systems using the 🧊LLLM framework I developed. Check live demos of my flagship systems above (click to explore, swipe left-right). In particular, I developed a web app 🧠Analytica (Research Preview Demo) for LLM-agentic probabilistic analysis.
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. -
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
JCISE
Powered by Jekyll and Minimal Light theme.