I am a fourth-year Ph.D. candidate at Dartmouth College, advised by Prof. Peter Chin. I am also a fully funded PhD Innovation Fellow (NSF Research Traineeship, Thayer Engineering & Tuck Business collaboration), supervised by Prof. Eric R. Fossum on research translation and entrepreneurship. I also hold an M.S. in CS (Intelligent Robotics) from USC, following graduate studies in Robotic Engineering at WPI. Previously, I interned at Microsoft Research Redmond and the Allen Institute for AI (Ai2).
Grounded in the LM/DL stack, from representation learning (ICLR’24), multimodal Transformer architecture for video (EMNLP’21) and program analysis (arXiv’21a, arXiv’21b), automatic pre-training and architecture design (NeurIPS’25 Spotlight “Genesys”), to agentic systems for society (ICLR’24 Spotlight “SocioDojo”), probabilistic analysis (ICLR’26 “Analytica”), and finance (FinAI@ICLR’25), my goal is to build the Autonomous Agentic Systems that can reliably take over critical domains:

I have built multiple complex LLM-agentic systems using the 🧊LLLM framework I developed. Check live demos of my flagship systems below (click to explore, swipe left-right). In particular, I developed an 🧠Analytica web app (Research Preview Demo) for LLM-agentic probabilistic analysis.
Robust and efficient wide and deep LLM-agentic analysis and forecasting with soft logic and parallel Jupyter Notebook analysts.
Distributed discovery system for novel language model architectures with autonomous design and evaluation.
Large-scale app synthesizer that models the full lifecycle autonomously, optimizing user demands with multi-thread CUA evaluators.
LLM agentic lifelong societal modeling and analysis with news feed and real-time data flow. A "Human World Model".
ICLR
NeurIPS
FinAI@ICLR
ICLR
ICLR
EMNLP
arXiv
arXiv
RNA biology
Powered by Jekyll and Minimal Light theme.