Hi, I'm Zifeng Wang, a Computer Science Ph.D. from UIUC. I work on AI4AI and recursive self-improvement for science: AI systems that design, evaluate, and improve other AI systems through reliable scientific feedback. My research connects two directions:

AI4AI & Scientific Agents — exploring agents that design experiments, build and evaluate models, and use the results to improve the next generation of scientific AI.
Scientific Verifiers & World Models — developing simulations, evaluation methods, and feedback environments that help scientific agents test ideas and learn from evidence.
Current Focus

Closing the loop between proposing scientific ideas, testing them with reliable feedback, and using the results to improve both AI agents and their models of the world.

News

Show more ↓

Recent Talks

2026 Empowering Clinical Development with LLMs and AI Agents
DBMI @ Columbia · BIDS @ Yale · CSE @ CUHK · Tsinghua Medicine · Duke-NUS Medicine · CS @ Zhejiang · CS @ Tsinghua · SIGS @ Tsinghua · AI4S @ Peking · XtalPi
2025 Large language models for clinical trial design, execution, and analysis
AI for Health Webinar @ Sunlab, UIUC
2025 Medical scientific discovery in the era of large language models (Chinese)
HIT Webinar · Zuozhu's Lab @ Zhejiang University
Show more ↓

Selected Publications

TrialPanorama
Benchmarking and Developing Large Language Models Using One Million Clinical Trials
Zifeng Wang, Jiacheng Lin, Qiao Jin, Junyi Gao, Jathurshan Pradeepkumar, Pengcheng Jiang, Zhiyong Lu, Jimeng Sun.
npj Digital Medicine, 2026
[Paper] [Project] [Dataset] [Models]
News Coverage: Nature Biotechnology, MIT Technology Review, HyperAI
DeepEvidence
Empowering Biomedical Evidence Exploration and Synthesis with Deep Knowledge Graph Research
Zifeng Wang, Zheng Chen, Ziwei Yang, Xiao Wang, Qiao Jin, Yifan Peng, Zhiyong Lu, Jimeng Sun.
Nature Machine Intelligence, 2026
[Paper] [Code] [Dataset]
Data science copilots
Making Large Language Models Reliable Data Science Programming Copilots for Biomedical Research
Zifeng Wang, Benjamin Danek, Ziwei Yang, Zheng Chen, Jimeng Sun.
Nature Biomedical Engineering, 2026
[Paper] [Code] [Dataset]
News Coverage: Live Science
LEADS
A foundation model for human-AI collaboration in medical literature mining (LEADS)
Zifeng Wang, Lang Cao, Qiao Jin, Joey Chan, Nicholas Wan, Behdad Afzali, Hyun-Jin Cho, Chang-In Choi, Mehdi Emamverdi, Manjot K. Gill, Sun-Hyung Kim, Yijia Li, Yi Liu, Yiming Luo, Hanley Ong, Justin Rousseau, Irfan Sheikh, Jenny J. Wei, Ziyang Xu, Christopher M. Zallek, Kyungsang Kim, Yifan Peng, Zhiyong Lu, Jimeng Sun.
Nature Communications, 2025
[Paper] [Code] [Model] [Dataset]
Clinical evidence synthesis
Accelerating Clinical Evidence Synthesis with Large Language Models
Zifeng Wang, Lang Cao, Benjamin Danek, Qiao Jin, Zhiyong Lu, Jimeng Sun.
npj Digital Medicine, 2025
[Paper] [Dataset]
TrialGPT
Matching Patients to Clinical Trials with Large Language Models (TrialGPT)
Qiao Jin, Zifeng Wang, Charalampos S. Floudas, Fangyuan Chen, Changlin Gong, Dara Bracken-Clarke, Elisabetta Xue, Yifan Yang, Jimeng Sun, Zhiyong Lu.
Nature Communications, 2024
[Paper] [Code] [Dataset]
News Coverage: Nature, NIH News, NIH Director's Blog, Health Science Top 25 of 2024, POLITICO, AUA News, Azure Government, Informa, FedScoop, MSN

Media Coverage