Hello! 🤗

I'm Dequan Wang

Associate Professor at SJTU & SII

About

I am Dequan Wang (王德泉), an associate professor at Shanghai Jiao Tong University and a full-time mentor at Shanghai Innovation Institute.

My research explores the intersection of Agentic AI and multi-disciplinary applications. I develop autonomous multi-agent systems optimized for coding, natural science, and social science.

My work focuses on building the next generation of agency-first AI that is efficient, evaluable, and capable of solving real-world challenges from the molecular level to the societal scale.

I completed my Ph.D. at University of California, Berkeley, advised by Prof. Trevor Darrell, and earned my B.S. from Fudan University.

Agentic AI AI for Science

Positions

Associate Professor

Shanghai Jiao Tong University

2026 - Present

Full-time Mentor

Shanghai Innovation Institute

2025 - Present

Research Scientist

Shanghai Artificial Intelligence Laboratory

2023 - 2024

Assistant Professor

Shanghai Jiao Tong University

2023 - 2025

Education

Ph.D. in Computer Science

University of California, Berkeley

2016 - 2022

B.S. in Computer Science

Fudan University

2012 - 2016

Papers

  1. Data-Centric Foundation Models in Computational Healthcare: A Survey

    Yunkun Zhang*, Jin Gao*, Zheling Tan, Lingfeng Zhou, Kexin Ding, Mu Zhou, Shaoting Zhang#, Dequan Wang#

    ACM Computing Surveys (2026)
  2. Measuring Bias Amplification in Multi-Agent Systems with Large Language Models

    Keyu Li, Jin Gao, Dequan Wang

    ICLR 2026
  3. Credit-Budgeted ICPC-Style Coding: When LLM Agents Must Pay for Every Decision

    Lingfeng Zhou, Junhao Shi, Jin Gao, Dequan Wang

    ICLR 2026
  4. From Natural Discovery to AI-Guided Design: A Curated Collection of Compact Enhancers for Crop Engineering

    Qi Yao*, Jin Gao*, Keling Wang*, Yufeng Liu*, Peijin Han, Hong Pan, Xiaofeng Yang, Qianlan Yin, Dating Zhong, Lu Ye, Qi Deng, Lingling Gao, Xiaoyu Tu, Dequan Wang#, Yuming Lu#

    ADVANCED SCIENCE (2026)
  5. PersonaEval: Are LLM Evaluators Human Enough to Judge Role-Play?

    Lingfeng Zhou, Jialing Zhang, Jin Gao, Mohan Jiang, Dequan Wang

    COLM 2025
  6. MAC: A Live Benchmark for Multimodal Large Language Models in Scientific Understanding

    Mohan Jiang*, Jin Gao*, Jiahao Zhan, Dequan Wang

    COLM 2025
  7. AI4Protein: Transforming the Future of Protein Design

    Dequan Wang*, Zheling Tan*, Jin Gao*, Shaoting Zhang, Jiaqi Shen, Yuming Lu

    SCIENCE CHINA Life Sciences (2025)
  8. Dissecting Dissonance: Benchmarking Large Multimodal Models Against Self-Contradictory Instructions

    Jin Gao, Lei Gan, Yuankai Li, Yixin Ye, Dequan Wang

    ECCV 2024
  9. Lost in Translation: Latent Concept Misalignment in Text-to-Image Diffusion Models

    Juntu Zhao, Junyu Deng*, Yixin Ye*, Chongxuan Li, Zhijie Deng#, Dequan Wang#

    ECCV 2024
  10. MedFMC: A Real-world Dataset and Benchmark for Foundation Model Adaptation in Medical Image Classification

    Dequan Wang*, Xiaosong Wang*, Lilong Wang, Mengzhang Li, Qian Da, Xiaoqiang Liu, Xiangyu Gao, Jun Shen, Junjun He, Tian Shen, Qi Duan, Jie Zhao, Kang Li, Yu Qiao#, Shaoting Zhang#

    Scientific Data (2023)
  11. Text-guided Foundation Model Adaptation for Pathological Image Classification

    Yunkun Zhang, Jin Gao, Mu Zhou, Xiaosong Wang, Yu Qiao, Shaoting Zhang, Dequan Wang

    MICCAI 2023
  12. Back to the Source: Diffusion-Driven Adaptation to Test-Time Corruption

    Jin Gao*, Jialing Zhang*, Xihui Liu, Trevor Darrell, Evan Shelhamer#, Dequan Wang#

    CVPR 2023