I am currently a Postdoctoral Fellow at The University of Hong Kong (working with Prof. Ping Luo). I received my Ph.D. degree from Northwestern Polytechnical University under the supervision of Prof. Xuelong Li and my B.Eng. degree from Xidian University.

My research interests include representation learning, multimodal understanding, and mulitimodal generation. I’m trying extending our techniques to embodied AI as well. Please feel free to contact me if you are interested in collaboration. I would be happy to discuss potential opportunities.

Research Interests

Representation Learning

  • Multimodal Representation
  • Noise Learning

Multimodal Understanding

  • MLLM Post-Training
  • 3D Vision Foundation Model

Multimodal Generation

  • Controllable Generation
  • Few-Step Generation

News

  • [Oct. 2026] One paper is accepted by IEEE Transactions on Multimedia.
  • [Sep. 2026] One paper is accepted by Information Fusion.
  • [Aug. 2026] One paper is accepted by Pattern Recognition.
  • [Aug. 2026] We will organize a Special Session on ICASSP 2027.
  • [Jul. 2026] One paper is accepted by IEEE RAL.
  • [Jul. 2026] Invited as a Senior Program Committee (SPC) of AAAI 2027.
  • [Jul. 2026] One paper is accepted by IEEE TIP.
  • [Jul. 2026] Two papers are accepted by ACM MM 2026.
  • [Jun. 2026] One paper is accepted by Pattern Recognition.
  • [May 2026] Four papers are accepted by ICML-2026.
  • [Apr. 2026] One paper is accepted by TMLR.
  • [Mar. 2026] One paper is accepted by TVCG.
  • [Mar. 2026] One paper is accepted by TVCG.
  • [Jan. 2026] One paper is accepted by CVPR-2026 and one paper is accepted by CVPR-2026 Findings.
  • [Jan. 2026] Two papers are accepted by ICLR-2026.
  • [Nov. 2025] Four papers (oral * 2) are accepted by AAAI-2026.
  • [Sep. 2025] Two papers are accepted by NeurIPS-2025.
  • [Jul. 2025] One paper is accepted by Pattern Recognition Letters.
  • [Jul. 2025] One paper is accepted by TITS.
  • [Jun. 2025] One paper is accepted by TPAMI.
  • [May 2025] One paper is accepted by TPAMI.
  • [May 2025] One paper is accepted by ACL-2025 Findings.
  • [May 2025] One paper is accepted by ICML-2025.
  • [Feb. 2025] Two papers (oral * 1) are accepted by CVPR-2025.
  • [Dec. 2024] One paper is accepted by TNNLS.
  • [Dec. 2024] We will organize The 4th Anti-UAV Workshop & Challenge on CVPR-2025.
  • [Dec. 2024] Three papers are accepted by AAAI-2025.

Call for Papers

  • [Ongoing] We are organizing a special session, Generative Transmission for Distributed Intelligent Signal Processing based on Large Foundation Models and Beneficial Noise Models, on ICASSP 2027 (CCF-B), where I’m the Co-Chair. Welcome to submit your manuscripts about noise and generative models to our special session. If you have any questions about our special session, please feel free to contact me (hyzhang98@gmail.com).
  • [Ongoing] We are organizing a special issue, Beneficial Noise Processing in Multimodal Signal Processing, on Signal Processing (Impact Factor = 3.6), where I’m the Executive Guest Editor. The homepage is here. Welcome to submit your manuscripts about noise to our special issue. If you have any questions about our special issues, please feel free to contact me (hyzhang98@gmail.com).
  • [Closed] We are organizing a special issue, Beneficial Noise Learning, on Pattern Recognition (Impact Factor > 7), where I’m the Executive Guest Editor. The homepage is here. Welcome to submit your manuscripts about noise (such as diffusion models, flow-based models, adversarial models, noisy labels, uncertainty, label smoothing, etc.) to our special issue. If you have any questions about our special issues, please feel free to contact me (hyzhang98@gmail.com).
  • [Closed] We are organizing a special issue, Spatial Embodied Intelligence of Unmanned Systems in Open Urban Environments, on Pattern Recognition (Impact Factor > 7), where I’m the Executive Guest Editor. The homepage is here. Welcome to submit your manuscripts about Embodied AI to our special issue. If you have any questions about our special issues, please feel free to contact me (hyzhang98@gmail.com).
  • [Closed] We are organizing a special issue, Positive Noise Learning, on Neurocomputing (Impact Factor > 6), where I’m the Executive Guest Editor.The homepage is here. Welcome to submit your manuscripts about noise (such as diffusion models, flow-based models, adversarial models, noisy labels, uncertainty, label smoothing, etc.) to our special issue. If you have any questions about our special issues, please feel free to contact me (hyzhang98@gmail.com).

Recent Works

Multimodal Continual Learning with MLLMs from Multi-Scenario Perspectives

Multimodal Continual Learning with MLLMs from Multi-Scenario Perspectives

Kai Jiang, Siqi Huang, Xiangyu Chen, Jiawei Shao, Hongyuan Zhang*, Ping Luo, Xuelong Li*

The first cross-device continual multimodal understanding dataset and model

arxiv

AHAP: Reconstructing Arbitrary Humans from Arbitrary Perspectives with Geometric Priors

AHAP: Reconstructing Arbitrary Humans from Arbitrary Perspectives with Geometric Priors

Xiaozhen Qiao, Wenjia Wang, Zhiyuan Zhao, Jiacheng Sun, Ping Luo, Hongyuan Zhang*, Xuelong Li*

A feedforward framework for reconstructing arbitrary humans (and scene) from arbitrary camera perspectives

arxiv

Safeguarding Text-to-Image Generative Models Against Unauthorized Knowledge Distillation

Safeguarding Text-to-Image Generative Models Against Unauthorized Knowledge Distillation

Yilan Gao, Sida Huang, Hongyuan Zhang*, Xuelong Li*

A model trying preventing data distillation on text-to-image generation

arxiv

Latent Noise Mask for Reducing Visual Redundancy in Multimodal Large Language Models

Latent Noise Mask for Reducing Visual Redundancy in Multimodal Large Language Models

Kai Jiang, Ruishu Zhu, Siqi Huang, Hongyuan Zhang*, Xuelong Li*

A reasoning framework that empowers MLLMs to reason with cleaner visual cues via noise masking

arxiv

Selected Publications

The full list of my papers can be found on my Google Scholar or here.
Data Augmentation of Contrastive Learning is Estimating Positive-incentive Noise

Data Augmentation of Contrastive Learning is Estimating Positive-incentive Noise

Hongyuan Zhang, Yanchen Xu, Sida Huang, and Xuelong Li

International Conference on Machine Learning (ICML) , 2026

paper | code

Variational Positive-incentive Noise: How Noise Benefits Models

Variational Positive-incentive Noise: How Noise Benefits Models

Hongyuan Zhang, Sida Huang, Yubin Guo, and Xuelong Li

IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI ) , 2025

paper | code

Decouple Graph Neural Networks: Train Multiple Simple GNNs Simultaneously Instead of One

Decouple Graph Neural Networks: Train Multiple Simple GNNs Simultaneously Instead of One

Hongyuan Zhang, Yanan Zhu, and Xuelong Li

IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI ) , 2024

paper | code

Non-Graph Data Clustering via O(n) Bipartite Graph Convolution

Non-Graph Data Clustering via O(n) Bipartite Graph Convolution

Hongyuan Zhang, Jiankun Shi, Rui Zhang, and Xuelong Li

IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI ) , 2023

paper | code

CNN2GNN: How to Bridge CNN with GNN

CNN2GNN: How to Bridge CNN with GNN

Ziheng Jiao, Hongyuan Zhang*, and Xuelong Li*

IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI ) , 2025

paper

ViewMask-1-to-3: Multi-View Consistent Image Generation via Multimodal Discrete Diffusion Models

ViewMask-1-to-3: Multi-View Consistent Image Generation via Multimodal Discrete Diffusion Models

Ruishu Zhu, Zhihao Huang, Jiacheng Sun, Ping Luo, Hongyuan Zhang*, and Xuelong Li*

International Conference on Machine Learning (ICML) , 2026

paper | code

On-Policy Distillation for Vision-Language Model Adaptation: An Effective Paradigm on Low-Quality Multimodal Data

On-Policy Distillation for Vision-Language Model Adaptation: An Effective Paradigm on Low-Quality Multimodal Data

Hongyuan Zhang+, Xianda Guo+, Yanlun Peng+, Qianlong Yang, Yubin Guo, Pinhan Fu, Mulin Chen, Xiaozhen Qiao, and Ping Luo

Information Fusion , 2026

paper

Rectified Noise: A Generative Model Using Positive-incentive Noise

Rectified Noise: A Generative Model Using Positive-incentive Noise

Zhenyu Gu, Yanchen Xu, Sida Huang, Yubin Guo, and Hongyuan Zhang*

Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), oral , 2026

paper | code

Laytrol: Preserving Pretrained Knowledge in Layout Control for Multimodal Diffusion Transformers

Laytrol: Preserving Pretrained Knowledge in Layout Control for Multimodal Diffusion Transformers

Sida Huang, Siqi Huang, Ping Luo, and Hongyuan Zhang*

Proceedings of the AAAI Conference on Artificial Intelligence (AAAI) , 2026

paper | code

Explore How To Inject Beneficial Noise in MLLMs

Explore How To Inject Beneficial Noise in MLLMs

Ruishu Zhu, Sida Huang, Ziheng Jiao, and Hongyuan Zhang*

Proceedings of the AAAI Conference on Artificial Intelligence (AAAI) , 2026

paper | code

CoLM: Collaborative Large Models via A Client-Server Paradigm

CoLM: Collaborative Large Models via A Client-Server Paradigm

Siqi Huang, Sida Huang, and Hongyuan Zhang*

Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), oral , 2026

paper

Mixture of Noise for Pre-Trained Model-Based Class-Incremental Learning

Mixture of Noise for Pre-Trained Model-Based Class-Incremental Learning

Kai Jiang, Zhengyan Shi, Dell Zhang, Hongyuan Zhang*, and Xuelong Li*

The Thirty-Ninth Annual Conference on Neural Information Processing Systems (NeurIPS) , 2025

paper | code

NFIG: Multi-Scale Autoregressive Image Generation via Frequency Ordering

NFIG: Multi-Scale Autoregressive Image Generation via Frequency Ordering

Zhihao Huang, Xi Qiu, Yukuo Ma, Yifu Zhou, Hongyuan Zhang*, Chi Zhang*, and Xuelong Li*

The Thirty-Ninth Annual Conference on Neural Information Processing Systems (NeurIPS) , 2025

paper | code

Learn Positive-incentive Noise As Graph Augmentation

Learn Positive-incentive Noise As Graph Augmentation

Siqi Huang, Yanchen Xu, Hongyuan Zhang*, and Xuelong Li*

International Conference on Machine Learning (ICML) , 2025

paper | code

Adv-CPG: Facial Adversarial Attacks for Customized Portrait Generation

Adv-CPG: Facial Adversarial Attacks for Customized Portrait Generation

Junying Wang, Hongyuan Zhang, and Yuan Yuan

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), oral , 2025

paper | code

Enhance Vision-Language Alignment with Noise

Enhance Vision-Language Alignment with Noise

Sida Huang, Hongyuan Zhang*, and Xuelong Li*

Proceedings of the AAAI Conference on Artificial Intelligence (AAAI) , 2025

paper | code

Why Does Dropping Edges Usually Outperform Adding Edges in Graph Contrastive Learning?

Why Does Dropping Edges Usually Outperform Adding Edges in Graph Contrastive Learning?

Yanchen Xu, Siqi Huang, Hongyuan Zhang*, and Xuelong Li*

Proceedings of the AAAI Conference on Artificial Intelligence (AAAI) , 2025

paper | code

Towards Projected Clustering with Aggregated Mapping

Towards Projected Clustering with Aggregated Mapping

Hongyuan Zhang, Yanan Zhu, and Rui Zhang,

IEEE Transactions on Image Processing (T-IP) , 2023

paper | code

Matrix Completion via Non-Convex Relaxation and Adaptive Correlation Learning

Matrix Completion via Non-Convex Relaxation and Adaptive Correlation Learning

Xuelong Li, Hongyuan Zhang, and Rui Zhang,

IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI ) , 2023

paper | code

Adaptive Graph Auto-Encoder for General Data Clustering

Adaptive Graph Auto-Encoder for General Data Clustering

Xuelong Li, Hongyuan Zhang, and Rui Zhang,

IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI ) , 2022

paper | code

View full publication list →

Part of Service

Editor of Journal

  • Associate Editor of IEEE Transactions on Fuzzy Systems
  • Associate Editor of Pattern Recognition
  • Associate Editor of Neurocomputing

Area Chair / Senior Program Committee Member

  • Senior Program Committee Member (SPC) of AAAI Conference on Artificial Intelligence (AAAI 27)

Organizer / Chair

  • Co-Chair of the ICASSP 2027 Special Session on Generative Transmission for Distributed Intelligent Signal Processing

Reviewer

  • ICML / ICLR / NeurIPS / CVPR / ICCV / ECCV / AAAI / AISTATS / SIGKDD / IJCAI / ACM MM / ICDM / …
  • IEEE TPAMI / TIP / TNNLS / TCyb / TMM / …