Mingze Yuan

I am a third-year Ph.D. student in Computer Science at Harvard University, advised by Prof. Na Li and Prof. Quanzheng Li at Harvard Medical School. I also work with Prof. Wengong Jin at Northeastern University.

Previously, I received an M.S. in Data Science (2024) and a B.S. in Statistics, with a second degree in Economics (2021), from Peking University. I was advised by Prof. Bin Dong and was a research intern at Alibaba DAMO Academy (2022–2024).

Email  /  Google Scholar  /  GitHub  /  CV  /  LinkedIn

profile photo
Research

My research spans generative modeling and large language models (LLMs). I currently focus on (1) self-improving agents for scientific discovery, particularly molecular discovery and spatial biology, and (2) LLM reasoning. My earlier work includes diffusion models and their applications to medical imaging.

Selected Publications* Equal contribution

Select a figure to view it at full size in a new tab.

MoLRSI Figure 1c, showing memory-guided workflow optimization and cross-task memory

MoLRSI: A Recursive Self-Improving AI Agent for Molecular Discovery
Yikun Zhang*, Xiwei Cheng*, Mingze Yuan*, et al.
arXiv preprint, 2026
Co-first authorship to be reflected in a forthcoming revision.

FuseMap spatial transcriptomics embeddings and molecular coordinate framework for the mouse brain

An agentic AI spatial molecular foundation model of the brain
Yichun He, Hao Sheng, Mingze Yuan, et al.
Nature Methods, accepted in principle, 2026

Figure 2, showing unseen mixed-depth interfaces and causal loop forcing

Ready to Read, Not Ready to Reuse: Mixed-Depth Interfaces in Looped Language Models
Mingze Yuan, Na Li, Quanzheng Li, Huangjie Zheng
Manuscript, 2026

DIAMOND pipeline for generating virtual contrast-enhanced CT images

High-fidelity virtual contrast-enhanced CT via generative artificial intelligence for pancreatic oncology: a retrospective multicentre study
Boxiang Yun*, Mingze Yuan*, et al.
The Lancet Digital Health, accepted in principle, 2026
* Equal contribution.

DynaReason-Pro Figure 1a, showing protein function prediction from conformational ensembles

Beyond Static Structures: Linking Protein Dynamics to Function via DynaReason-Pro
Zhaokang Liang, Mingze Yuan, Quanzheng Li, Wengong Jin
Transactions on Machine Learning Research (TMLR), accepted in principle, 2026

PIRF overview for physics-informed diffusion model fine-tuning

PIRF: Physics-Informed Reward Fine-Tuning for Diffusion Models.
Mingze Yuan, Pengfei Jin, Na Li, Quanzheng Li
NeurIPS workshop in AI4Science, 2025

paper  |  arXiv  |  code
RODS overview for detecting and reducing diffusion model hallucinations

RODS: Robust Optimization Inspired Diffusion Sampling for Detecting and Reducing Hallucination in Generative Models
Yiqi Tian*, Pengfei Jin*, Mingze Yuan, Na Li, Bo Zeng, Quanzheng Li
NeurIPS, 2025

paper  |  arXiv
Mask transformer overview for medical image segmentation and out-of-distribution localization

Devil is in the Queries: Advancing Mask Transformers for Real-world Medical Image Segmentation and Out-of-Distribution Localization
Mingze Yuan, Yingda Xia, Hexin Dong, Zifan Chen, Jiawen Yao, Mingyan Qiu, Ke Yan, Xiaoli Yin, Yu Shi, Xin Chen, Zaiyi Liu, Bin Dong, Jingren Zhou, Le Lu, Ling Zhang, Li Zhang
CVPR, 2023 Highlight

Top 2.5%


paper  |  arXiv
Cluster-induced mask transformer overview for gastric cancer screening on CT

Cluster-Induced Mask Transformers for Effective Opportunistic Gastric Cancer Screening on Non-contrast CT Scans
Mingze Yuan, Yingda Xia, Xin Chen, Jiawen Yao, Junli Wang, Mingyan Qiu, Hexin Dong, Jingren Zhou, Bin Dong, Le Lu, Li Zhang, Zaiyi Liu, Ling Zhang
MICCAI, 2023

paper  |  arXiv
Illustration from Unsupervised Image Denoising with Score Function

Unsupervised Image Denoising with Score Function
Yutong Xie, Mingze Yuan, Bin Dong, Quanzheng Li
NeurIPS, 2023

Academic Service
  • Journal reviewer: IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)
  • Conference reviewer: ICML, NeurIPS, RSS, ICLR, MICCAI
Selected Honors and Awards

  • Citadel NeurIPS travel grant, 2025
  • Gold Medal, 32nd China Mathematics Olympiad (CMO), 2016
  • China National Scholarship, Peking University, 2023


Last update: Nov 2026