Juncheng Wu

About Me

I am a Ph.D. student at VLAA Lab in University of California, Santa Cruz. I am fortunate to work with Prof. Yuyin Zhou and Cihang Xie. I received bachelor degree in Tongji University, where I am fortunate to be advised by Prof. Zhangkai Ni.

My research interest lies in Medical Foundation Models. I currently focus on building powerful reasoning (Multimodal) Large Language Models (LLMs) for medical tasks.

Research Interests

Large Language Models: Multimodal Large Language Models, LLMs Post-training, Test-time Scaling.

News

[Apr. 2025] We release MedReason, a large-scale high-quality medical reasoning dataset designed to enable faithful medical reasoning. And another two papers about medical test-time scaling and safety reasoning.
[Mar. 2025] I will join Amazon Inc. as a Applied Scientist Intern in Summer 2025, supervised by Xianfeng Tang. Looking forward to the wonderful research experience there!
[Feb. 2025] We release EpiFoundation, a foundation model for scATAC-seq based on aligning peak-to-gene correlations.
[Jan. 2025] One paper is accepted to ICLR 2025.
[Sep. 2024] One paper is accepted to NeurIPS 2024.
[Sep. 2024] We comprehensively benchmarked openai o1-preview on multiple medical tasks, and provide a detailed analysis of its performance. Project Page
[Aug. 2024] We release MedTrinity-25M, a large-scale multimodal dataset for medicine, covering over 25 million images across 10 modalities, with multigranular annotations.
[Jun. 2024] Obtained the honor of Outstanding Graduate of Tongji University.
[Feb. 2024] Our paper about misalignment robust loss function is accepted to CVPR 2024.

Publications

preprint

MedReason: Eliciting Factual Medical Reasoning Steps in LLMs via Knowledge Graphs

Juncheng Wu*, Wenlong Deng*, Xingxuan Li, Sheng Liu, Taomian Mi, Yifan Peng, Ziyang Xu, Yi Liu, Hyunjin Cho, Chang-In Choi, Yihan Cao, Hui Ren, Xiang Li, Xiaoxiao Li, Yuyin Zhou

ArXiv preprint, 2025.

PDF Code

preprint

EpiFoundation: A Foundation Model for Single-Cell ATAC-seq via Peak-to-Gene Alignment

Juncheng Wu, Changxin Wan, Zhicheng Ji, Yuyin Zhou, Wenpin Hou

bioRxiv preprint, 2025.

PDF Code

Neurips

DDR: Exploiting Deep Degradation Response as Flexible Image Descriptor

Juncheng Wu, Zhangkai Ni, Hanli Wang, Wenhan Yang, Yuyin Zhou, Shiqi Wang

Annual Conference on Neural Information Processing Systems (Neurips), 2024.

PDF Code

preprint

A Preliminary Study of o1 in Medicine: Are We Closer to an AI Doctor?

Yunfei Xie*, Juncheng Wu*, Haoqin Tu*, Siwei Yang*, Bingchen Zhao, Yongshuo Zong, Qiao Jin, Cihang Xie, Yuyin Zhou

ArXiv preprint, 2024.

PDF Project Page

ICLR

MedTrinity-25M: A Large-scale Multimodal Dataset with Multigranular Annotations for Medicine

Yunfei Xie*, Ce Zhou*, Lang Gao*, Juncheng Wu*, Xianhang Li, Hong-Yu Zhou, Sheng Liu, Lei Xing, James Zou, Cihang Xie, Yuyin Zhou

The Thirteenth International Conference on Learning Representations (ICLR), 2025.

PDF Code Project Page

preprint

Restorer: Removing Multi-Degradation with All-Axis Attention and Prompt Guidance

Jiawei Mao, Juncheng Wu, Yuyin Zhou, Xuesong Yin, Yuanqi Chang

ArXiv preprint, 2024.

PDF

CVPR

Misalignment-Robust Frequency Distribution Loss for Image Transformation

Zhangkai Ni, Juncheng Wu*, Zian Wang*, Wenhan Yang, Hanli Wang, Lin Ma

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024.

PDF Code

preprint

m1: Unleash the Potential of Test-Time Scaling for Medical Reasoning with Large Language Models

Xiaoke Huang, Juncheng Wu, Hui Liu, Xianfeng Tang, Yuyin Zhou

ArXiv preprint, 2025.

PDF Code

preprint

STAR-1: Safer Alignment of Reasoning LLMs with 1K Data

Zijun Wang, Haoqin Tu, Yuhan Wang, Juncheng Wu, Jieru Mei, Brian R. Bartoldson, Bhavya Kailkhura, Cihang Xie

ArXiv preprint, 2025.

PDF Code

About Me

Research Interests

News

Publications

Services

Conference Reviewers