Wenlong Zhang

Young Researcher in AI4Science, Shanghai AI Lab
zhangwenlong@pjlab.org.cn
Google scholar | Github | Researchgate

I am a Young Researcher with OpenScienceLab at Shanghai AI Lab, working with Prof. Wanli Ouyang and Prof. Lei Bai. Before that, I got the PhD degree from Hong Kong Polytechnic University, working with Prof. Xiao-Ming Wu. I also interned at XPixel group in Shanghai AI Lab and SIAT-CAS, working with Prof. Chao Dong and Prof. Yu Qiao. In 2018, I got the Master degree from the Beijing Institute of Technology, supervised by Prof. Weidong Hu.

I am passionate about exploring advanced AGI model to address challenges across large-scale scientific scenario. Recently, my primary areas of focus include:

Large foundation model: Developing general foundational model for the unified representation and processing of large-scale data and tasks in earth science.
Multimodel learning: Building scientifical multimodal data and model for knowledge understanding.
LLM-based multi-agent: Creating efficient LLM-based multi-agent system for knowledge discovery.
Generative model: Aiming to combine multi-source data and physical law for powerful scientific data synthesis.

If you are interested in the above research topics and would like to join us with research intern or Joint Training Ph.D. Project at Shanghai AI Lab, feel free to drop me an email zhangwenlong@pjlab.org.cn. Students with good foundations in AI background or earth science are appreciated.

news

Nov 08, 2024	Two papers were accepted by ICLR2025. Our WeatherGFM is the first generalist weather foundation model that can flexibly handle more than 10 weather understanding tasks. It outperforms ECMWF Integrated Forecasting System (IFS) forecast results.
Nov 07, 2024	One papers were accepted by ICASSP2025. We propose the first diffusion-based method, DiffSR, to synthesize weather radar data from meteorological satellite data.
Aug 21, 2024	One papers were accepted by EMNLP2024. One papers were accepted by NeurIPS.
Jul 04, 2024	One papers were accepted by ECCV. One papers were accepted by ACM MM.
Sep 22, 2023	One papers were accepted by NeurIPS. One papers were accepted by ICLR and was selected for an Spotlight presentation in December.
Nov 20, 2022	One papers were accepted by ICLR. One papers were accepted by CVPR workshop.
Jul 20, 2021	One papers were accepted by T-PAMI. One papers were accepted by NeurIPS.
May 20, 2019	One papers were accepted by ICCV and was selected for an oral presentation.

selected publications

ICLR

WeatherGFM: Learning A Weather Generalist Foundation Model via In-context Learning

Xiangyu Zhao , Zhiwang Zhou , Wenlong Zhang* , Yihao Liu , Xiangyu Chen , Junchao Gong , Hao Chen , Ben Fei , Shiqi Chen , Xiao-Ming Wu Wanli Ouyang , and Lei Bai

In International Conference on Learning Representations , 2025
ICLR

Postcast: Generalizable postprocessing for precipitation nowcasting via unsupervised blurriness modeling

Junchao Gong , Siwei Tu , Weidong Yang , Ben Fei , Kun Chen , Wenlong Zhang , Xiaokang Yang , Wanli Ouyang , and Lei Bai

In International Conference on Learning Representations , 2025
ICASSP

DiffSR: Learning Radar Reflectivity Synthesis via Diffusion Model from Satellite Observations

Xuming He , Zhiwang Zhou , Wenlong Zhang* , Xiangyu Zhao , Hao Chen , Shiqi Chen , and Lei Bai

In International Conference on Acoustics, Speech, and Signal Processing , 2025
Arxiv

Understanding Layer Significance in LLM Alignment

Guangyuan Shi , Zexin Lu , Xiaoyu Dong , Wenlong Zhang , Xuanyu Zhang , Yujie Feng , and Xiao-Ming Wu

In arXiv preprint arXiv:2410.17875 , 2024
arXiv

A Preliminary Exploration Towards General Image Restoration

Xiangtao Kong , Jinjin Gu , Yihao Liu , Wenlong Zhang , Xiangyu Chen , Yu Qiao , and Chao Dong

In arXiv , 2024

arXiv
EMNLP

UniFashion: A Unified Vision-Language Model for Multimodal Fashion Retrieval and Generation

Xiangyu Zhao , Yuehan Zhang , Wenlong Zhang , and Xiao-Ming Wu

In Empirical Methods in Natural Language Processing , 2024

arXiv
MM

Learning A Low-Level Vision Generalist via Visual Task Prompt

Xiangyu Chen , Yihao Liu , Yuandong Pu , Wenlong Zhang , Jiantao Zhou , Yu Qiao , and Chao Dong

In ACM Multimedia , 2024

arXiv

ECCV

GRIDS: Grouped Multiple-Degradation Restoration with Image Degradation Similarity

Shuo Cao , Yihao Liu , Wenlong Zhang , Yu Qiao , and Chao Dong

In European Conference on Computer Vision(ECCV) , 2024

arXiv Bib Code

@inproceedings{GRIDS,
  title = {GRIDS: Grouped Multiple-Degradation Restoration with Image Degradation Similarity},
  author = {Cao, Shuo and Liu, Yihao and Zhang, Wenlong and Qiao, Yu and Dong, Chao},
  booktitle = {European Conference on Computer Vision(ECCV)},
  year = {2024},
}

NeurIPS

Generalizing Weather Forecast to Fine-grained Temporal Scales via Physics-AI Hybrid Modeling

Wanghan Xu , Fenghua Ling , Wenlong Zhang , Tao Han , Hao Chen , Wanli Ouyang , and Lei Bai

In Advances in Neural Information Processing Systems , 2024

arXiv

ICLR Spotlight

SEAL: A Framework for Systematic Evaluation of Real-World Super-Resolution

Wenlong Zhang , Xiaohui Li , Xiangyu Chen , Yu Qiao , Xiao-Ming Wu , and Chao Dong

In International Conference on Learning Representations (ICLR Spotlight) , 2024

arXiv Bib Code

@inproceedings{zhang2023arxiv,
  title = {SEAL: A Framework for Systematic Evaluation of Real-World Super-Resolution},
  author = {Zhang, Wenlong and Li, Xiaohui and Chen, Xiangyu and Qiao, Yu and Wu, Xiao-Ming and Dong, Chao},
  booktitle = {International Conference on Learning Representations (ICLR Spotlight)},
  year = {2024},
}

arXiv

HAT: Hybrid Attention Transformer for Image Restoration

Xiangyu Chen , Xintao Wang , Wenlong Zhang , Xiangtao Kong , Yu Qiao , Jiantao Zhou , and Chao Dong

In arXiv preprint , 2023

arXiv Bib Code

@inproceedings{chen2023arxiv,
  title = {HAT: Hybrid Attention Transformer for Image Restoration},
  author = {Chen, Xiangyu and Wang, Xintao and Zhang, Wenlong and Kong, Xiangtao and Qiao, Yu and Zhou, Jiantao and Dong, Chao},
  booktitle = {arXiv preprint},
  year = {2023},
}

NeurIPS

Real-World Image Super-Resolution as Multi-Task Learning

Wenlong Zhang , Xiaohui Li , Guangyuan Shi , Xiangyu Chen , Yu Qiao , Xiaoyun Zhang , Xiao-Ming Wu , and Chao Dong

In Advances in Neural Information Processing Systems (NeurIPS) , 2023

arXiv Bib Code

@inproceedings{zhang2023tgsr,
  title = {Real-World Image Super-Resolution as Multi-Task Learning},
  author = {Zhang, Wenlong and Li, Xiaohui and Shi, Guangyuan and Chen, Xiangyu and Qiao, Yu and Zhang, Xiaoyun and Wu, Xiao-Ming and Dong, Chao},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2023},
}

ICLR

Recon: Reducing Conflicting Gradients From the Root For Multi-Task Learning

Guangyuan Shi , Qimai Li , Wenlong Zhang , Jiaxin Chen , and Xiao-Ming Wu

In The Eleventh International Conference on Learning Representations (ICLR) , 2023

arXiv Bib Code

@inproceedings{zhang2023tgss,
  title = {Recon: Reducing Conflicting Gradients From the Root For Multi-Task Learning},
  author = {Shi, Guangyuan and Li, Qimai and Zhang, Wenlong and Chen, Jiaxin and Wu, Xiao-Ming},
  booktitle = {The Eleventh International Conference on Learning Representations (ICLR)},
  year = {2023},
}

TGRS

Spatial Resolution Matching of Microwave Radiometer Measurements Using Iterative Deconvolution with Close Loop Priors (ICLP)

Zhiyu Yao , Weidong Hu , Zhiyan Feng , Wenlong Zhang , Yang Liu , Zhihao Xu , and Leo P Ligthart

In IEEE Transactions on Geoscience and Remote Sensing , 2023

arXiv Bib Code

@inproceedings{2023iclp,
  title = {Spatial Resolution Matching of Microwave Radiometer Measurements Using Iterative Deconvolution with Close Loop Priors (ICLP)},
  author = {Yao, Zhiyu and Hu, Weidong and Feng, Zhiyan and Zhang, Wenlong and Liu, Yang and Xu, Zhihao and Ligthart, Leo P},
  booktitle = {IEEE Transactions on Geoscience and Remote Sensing},
  year = {2023},
}

ICCV oral

Ranksrgan: Generative adversarial networks with ranker for image super-resolution

Wenlong Zhang , Yihao Liu , Chao Dong , and Yu Qiao

In Proceedings of the IEEE/CVF International Conference on Computer Vision , 2019

arXiv Bib Code Website

@inproceedings{zhang2019ranksrgan,
  title = {Ranksrgan: Generative adversarial networks with ranker for image super-resolution},
  author = {Zhang, Wenlong and Liu, Yihao and Dong, Chao and Qiao, Yu},
  booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision},
  pages = {3096--3105},
  year = {2019},
  google_scholar_id = {UnMImiUAAAAJ},
}

T-PAMI

Ranksrgan: Generative adversarial networks with ranker for image super-resolution

Wenlong Zhang , Yihao Liu , Chao Dong , and Yu Qiao

IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021

arXiv Bib Code Website

@article{wenlong2021ranksrgan,
  title = {Ranksrgan: Generative adversarial networks with ranker for image super-resolution},
  author = {Zhang, Wenlong and Liu, Yihao and Dong, Chao and Qiao, Yu},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2021},
  publisher = {IEEE},
}

NeurIPS spotlight

Overcoming Catastrophic Forgetting in Incremental Few-Shot Learning by Finding Flat Minima

Guangyuan Shi , Jiaxin Chen , Wenlong Zhang , Li-Ming Zhan , and Xiao-Ming Wu

Advances in Neural Information Processing Systems, 2021

arXiv Bib Code

@article{shi2021overcoming,
  title = {Overcoming Catastrophic Forgetting in Incremental Few-Shot Learning by Finding Flat Minima},
  author = {Shi, Guangyuan and Chen, Jiaxin and Zhang, Wenlong and Zhan, Li-Ming and Wu, Xiao-Ming},
  journal = {Advances in Neural Information Processing Systems},
  volume = {34},
  year = {2021},
}

CVPRw oral

A Closer Look at Blind Super-Resolution: Degradation Models, Baselines, and Performance Upper Bounds

Wenlong Zhang , Guangyuan Shi , Yihao Liu , Chao Dong , and Xiao-Ming Wu

In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops , Jun 2022

arXiv Bib Supp Code

@inproceedings{Zhang_2022_CVPR,
  author = {Zhang, Wenlong and Shi, Guangyuan and Liu, Yihao and Dong, Chao and Wu, Xiao-Ming},
  title = {A Closer Look at Blind Super-Resolution: Degradation Models, Baselines, and Performance Upper Bounds},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},
  month = jun,
  year = {2022},
  pages = {527-536},
}