Zhongqi (Nick) Yue's Homepage

Biography

I am a Presidential Postdoctoral Fellow (PPF, Principal Investigator), jointly affiliated with Nanyang Technological University and Chalmers University of Technology (with Prof. Fredrik D. Johansson). In 2023, I completed my Ph.D. in NTU under Alibaba Talent Program, supervised by Prof. Hanwang Zhang and co-supervised by Prof. Qianru Sun. During Ph.D., I did an internship in Sea working under Prof. Pan Zhou. Prior to that, I received my bachelor's degree from NTU in 2017 under MOE SM2 scholarship.

My research vision is to build efficient and trustworthy agents: lightweight interactive models that learn fast while remaining reliable under distribution shift and transparent in their decision-making. Driven by this vision, I have published in top-tier venues including NeurIPS, ICLR, CVPR, and ICCV, and routinely received oral and spotlight recognitions (including a CVPR 2025 Best Student Paper Honorable Mention).

News

[12, 2025] "When are radiology reports useful for training medical image classifiers" won the best paper award at MMRL4H.

[11, 2025] 1 paper accepted by AAAI 2026 as oral presentation.

[10, 2025] 1 paper accepted by NeurIPS Math-AI workshop. 1 paper accepted as EurIPS MMRL4H oral and MedEurIPS oral.

[10, 2025] 2 papers accepted by NeurIPS 2025.

[06, 2025] 2 papers accepted by ICCV 2025 (1 highlight).

[06, 2025] 2 papers accepted by CVPR 2025 (1 best student paper honorable mention and 1 oral presentation).

[05, 2025] Released Selftok technical report (image tokenization, MLLM pre-training and post-training).

[02, 2025] Continued the PPF in Chalmers University of Technology, Sweden.

[06, 2024] 1 paper about few-shot learning accepted by CVPR 2024.

[05, 2024] 1 paper about unsupervised representation learning accepted by ICLR 2024.

[02, 2024] Started the PPF in NTU.

[10, 2023] Started a research internship in Sea.

[09, 2023] 1 paper about unsupervised domain adaptation accepted by NeurIPS 2023.

[08, 2023] Awarded Wallenberg-NTU Presidential Postdoctoral Fellowship.

[07, 2023] 2 papers about open-world detection and fair face recognition are accepted by ICCV 2023.

[03, 2023] 1 paper about video anomaly detection accepted by CVPR 2023.

[08, 2022] Received 2022 PREMIA Best Paper Awards (The Gold Award).

[09, 2021] 1 paper about self-supervised learning accepted by NeurIPS 2022 (Spotlight).

[07, 2021] 1 paper about unsupervised domain adaptation accepted by ICCV 2021 (Oral).

[03, 2021] 1 paper about zero-shot learning accepted by CVPR 2021.

[09, 2020] 1 paper about few-shot learning accepted by NeurIPS 2020.

[05, 2020] Joined Alibaba Talent Program to do a Ph.D. in NTU.

Publications [Google Scholar]

LLMs and MLLMs

Expanding the Action Space of LLMs to Reason Beyond Language

Zhongqi Yue, Weishi Wang*, Yundaichuan Zhan, Juncheng Li, Daniel Dahlmeier, Fredrik D. Johansson

NeurIPS 2025 Math-AI

Paper Project Page

Generative Multimodal Pretraining with Discrete Diffusion Timestep Tokens

Kaihang Pan*, Wang Lin*, Zhongqi Yue*, Tenglong Ao, Liyu Jia, Wei Zhao, Juncheng Li, Siliang Tang, Hanwang Zhang

CVPR 2025

Best Student Paper Honorable Mention (top 0.05%)

Paper Project Page

Selftok: Discrete Visual Tokens of Autoregression, by Diffusion, and for Reasoning

Bohan Wang, Zhongqi Yue, Fengda Zhang, Shuo Chen, Li'an Bi, Junzhe Zhang, Xue Song, Kennard Yanting Chan, Jiachun Pan, Weijia Wu, Mingze Zhou, Wang Lin, Kaihang Pan, Saining Zhang, Liyu Jia, Wentao Hu, Wei Zhao, Hanwang Zhang

Technical Report

Paper Project Page

Selftok-Zero: Reinforcement Learning for Visual Generation via Discrete and Autoregressive Visual Tokens

Bohan Wang, Mingze Zhou, Zhongqi Yue, Wang Lin, Kaihang Pan, Liyu Jia, Wentao Hu, Wei Zhao, Hanwang Zhang

NeurIPS 2025

Paper Coming Soon

Object Fusion via Diffusion Time-step for Customized Image Editing with Single Example

Xue Song, Zhongqi Yue*, Jiequan Cui, Hanwang Zhang, Jingjing Chen

AAAI 2026

Oral

Paper Coming Soon

Mastering Collaborative Multi-Modal Data Selection: A Focus on Informativeness, Uniqueness, and Representativeness

Qifan Yu*, Zhebei Shen*, Zhongqi Yue*, Yang Wu, Wenqiao Zhang, Yunfei Li, Juncheng Li, Siliang Tang, Yueting Zhuang

ICCV 2025

Highlight (top 2%)

Paper Project Page

AnyEdit: Mastering Unified High-Quality Image Editing for Any Idea

Qifan Yu*, Wei Chow*, Zhongqi Yue*, Kaihang Pan, Yang Wu, Xiaoyang Wan, Juncheng Li, Siliang Tang, Hanwang Zhang, Yueting Zhuang

CVPR 2025

Oral (top 0.7%)

Paper Project Page

Counterfactual Evolution of Multimodal Datasets via Visual Programming

Minghe Gao*, Zhongqi Yue*, Wenjie Yan, Yihao Hu, Wei Ji, Siliang Tang, Jun Xiao, Tat-Seng Chua, Yueting Zhuang, Juncheng Li

NeurIPS 2025

Paper Coming Soon

Benchmarking Multimodal CoT Reward Model Stepwise by Visual Program

Minghe Gao, Xuqi Liu, Zhongqi Yue, Yang Wu, Shuang Chen, Juncheng Li, Siliang Tang, Fei Wu, Tat-Seng Chua, Yueting Zhuang

ICCV 2025

Paper Project Page

Representation Learning

Self-Supervised Learning Disentangled Group Representation as Feature

Tan Wang, Zhongqi Yue, Jianqiang Huang, Qianru Sun, Hanwang Zhang

NeurIPS 2021

Spotlight Presentation (top 3%) PREMIA Best Student Paper 2022

Paper Project Page

Exploring Diffusion Time-Steps for Unsupervised Representation Learning

Zhongqi Yue, Jiankun Wang, Qianru Sun, Lei Ji, Eric I-Chao Chang, Hanwang Zhang

ICLR 2024

Paper Project Page

Invariant Feature Regularization for Fair Face Recognition

Jiali Ma, Zhongqi Yue, Tomoyuki Kagaya, Tomoki Suzuki, Karlekar Jayashree, Sugiri Pranata, Hanwang Zhang

ICCV 2023

Paper Project Page

Generalization

training a medical image classifier w/ or w/o reports.

When are radiology reports useful for training medical image classifiers?

Herman Bergström, Zhongqi Yue, Fredrik D. Johansson

EurIPS 2025

MMRL4H Best Paper MedEurIPS Oral

Paper Project Page

Few-Shot Learner Parameterization by Diffusion Time-Steps

Zhongqi Yue, Pan Zhou, Richang Hong, Hanwang Zhang, Qianru Sun

CVPR 2024

Paper Project Page

Transporting Causal Mechanisms for Unsupervised Domain Adaptation

Zhongqi Yue, Qianru Sun, Xian-Sheng Hua, Hanwang Zhang

ICCV 2021

Oral Presentation (top 3%)

Paper Project Page

Make the U in UDA Matter: Invariant Consistency Learning for Unsupervised Domain Adaptation

Zhongqi Yue, Hanwang Zhang, Qianru Sun

NeurIPS 2023

Paper Project Page

Random Boxes Are Open-world Object Detectors

Yanghao Wang, Zhongqi Yue, Xian-Sheng Hua, Hanwang Zhang

ICCV 2023

Paper Project Page

Unbiased Multiple Instance Learning for Weakly Supervised Video Anomaly Detection

Hui Lv, Zhongqi Yue, Qianru Sun, Bin Luo, Zhen Cui, Hanwang Zhang

CVPR 2023

Paper Project Page

Counterfactual Zero-Shot and Open-Set Visual Recognition

Zhongqi Yue*, Tan Wang*, Qianru Sun, Xian-Sheng Hua, Hanwang Zhang

CVPR 2021

Paper Project Page

Interventional Few-Shot Learning

Zhongqi Yue, Hanwang Zhang, Qianru Sun, Xian-Sheng Hua

NeurIPS 2020

Paper Project Page

Zhongqi (Nick) Yue

Dr.

Biography

News

Publications [Google Scholar]

LLMs and MLLMs

Expanding the Action Space of LLMs to Reason Beyond Language

Generative Multimodal Pretraining with Discrete Diffusion Timestep Tokens

Selftok: Discrete Visual Tokens of Autoregression, by Diffusion, and for Reasoning

Selftok-Zero: Reinforcement Learning for Visual Generation via Discrete and Autoregressive Visual Tokens

Object Fusion via Diffusion Time-step for Customized Image Editing with Single Example

Mastering Collaborative Multi-Modal Data Selection: A Focus on Informativeness, Uniqueness, and Representativeness

AnyEdit: Mastering Unified High-Quality Image Editing for Any Idea

Counterfactual Evolution of Multimodal Datasets via Visual Programming

Benchmarking Multimodal CoT Reward Model Stepwise by Visual Program

Representation Learning

Self-Supervised Learning Disentangled Group Representation as Feature

Exploring Diffusion Time-Steps for Unsupervised Representation Learning

Invariant Feature Regularization for Fair Face Recognition

Generalization

When are radiology reports useful for training medical image classifiers?

Few-Shot Learner Parameterization by Diffusion Time-Steps

Transporting Causal Mechanisms for Unsupervised Domain Adaptation

Make the U in UDA Matter: Invariant Consistency Learning for Unsupervised Domain Adaptation

Random Boxes Are Open-world Object Detectors

Unbiased Multiple Instance Learning for Weakly Supervised Video Anomaly Detection

Counterfactual Zero-Shot and Open-Set Visual Recognition

Interventional Few-Shot Learning