Wenwei Zhang

Wenwei Zhang

Young Research Scientist, Shanghai AI Laboratory

Selected Publications

Intern-S1-Pro: Scientific Multimodal Foundation Model at Trillion Scale
Yicheng Zou, ..., Wenwei Zhang, et al.
arXiv, 2026
[Paper]
Long-horizon Reasoning Agent for Olympiad-Level Mathematical Problem Solving
Songyang Gao*, Yuzhe Gu*, Zijian Wu*, Lingkai Kong*, Wenwei Zhang*, et al.
arXiv, 2025
Officially ranked 3rd among human competitors and 1st among AI competitors in CMO2025.
[Paper]
Achieving Olympia-Level Geometry Large Language Model Agent via Complexity Boosting Reinforcement Learning
Haiteng Zhao*, Junhao Shen*, ..., Wenwei Zhang†, Kai Chen†
International Conference on Learning Representations (ICLR) , 2026
Surpasses AlphaGeometry2, SeedGeometry, and Human Gold Medalists.
[Paper] [Code] [Project Page]
Exploring the Limit of Outcome Reward for Learning Mathematical Reasoning
Chengqi Lyu*, Songyang Gao*, Yuzhe Gu*, Wenwei Zhang*†, ..., Kai Chen†
Conference on Language Modeling (COLM) , 2025
[Paper] [Code] [Project Page]
MindSearch: Mimicking Human Minds Elicits Deep AI Searcher
Zehui Chen*, Kuikun Liu*, Qiuchen Wang, Jiangning Liu, Wenwei Zhang, Kai Chen, Feng Zhao
International Conference on Learning Representations (ICLR) , 2025
[Paper] [Code] [Project Page]
InternLM: A Multilingual Language Model with Progressively Enhanced Capabilities
InternLM Team
GitHub, 2023
[Code] [Project Page]
MultiModal-GPT: A Vision and Language Model for Dialogue with Humans
Tao Gong*, Chengqi Lyu*, Shilong Zhang*, ..., Wenwei Zhang*, Ping Luo, Kai Chen
arXiv, 2023
[Paper] [Code] [Project Page]
Video K-Net: A Simple, Strong, and Unified Baseline for Video Segmentation
Xiangtai Li*, Wenwei Zhang*, Jiangmiao Pang*, Kai Chen, Guangliang Cheng, Yunhai Tong, Chen Change Loy
IEEE Conference on Computer Vision and Pattern Recognition (CVPR) , 2022 (oral)
[Paper] [Code] [Project Page]
K-Net: Towards Unified Image Segmentation
Wenwei Zhang, Jiangmiao Pang, Kai Chen, Chen Change Loy
Advances in Neural Information Processing Systems (NeurIPS) , 2021
New state of the art on COCO Panoptic Segmentation and ADE20K Semantic Segmentation datasets.
[Paper] [Code] [Project Page]
Seesaw Loss for Long-Tailed Instance Segmentation
Jiaqi Wang, Wenwei Zhang, Yuhang Zang, Yuhang Cao, Jiangmiao Pang, Tao Gong, Kai Chen, Ziwei Liu, Chen Change Loy, Dahua Lin
IEEE Conference on Computer Vision and Pattern Recognition (CVPR) , 2021
Key component for the 2nd runner-up method in LVIS Challenge 2020.
[Paper] [Code]
Exploring Data Augmentation for Multi-Modality 3D Object Detection
Wenwei Zhang, Zhe Wang, Chen Change Loy
International Conference on Learning Representations, Scene Representations For Autonomous Driving Workshop (ICLRW) , 2023
Method for the Best PKL Award in 3rd nuScenes detection challenge of 5th AI Driving Olympics, NeurIPS 2020
[Paper] [Code]
Side-Aware Boundary Localization for More Precise Object Detection
Jiaqi Wang, Wenwei Zhang, Yuhang Cao, Kai Chen, Jiangmiao Pang, Tao Gong, Jianping Shi, Chen Change Loy, Dahua Lin
European Conference on Computer Vision (ECCV) , 2020 (spotlight)
Key component for the 1st place method in COCO Detection Challenge 2019.
[Paper] [Code]
Robust Multi-Modality Multi-Object Tracking
Wenwei Zhang, Hui Zhou, Shuyang Sun, Zhe Wang, Jianping Shi, Chen Change Loy
International Conference on Computer Vision (ICCV) , 2019
[Paper] [Code] [Project Page] [Poster]
Before the Rise of Machines, The beginning of Consciousness and the Human Intelligence
H. J. Cai, Tianqi Cai, Wenwei Zhang, Kai Wang
Tsinghua University Press, 2017
Awarded the Wu Wenjun Award for Science and Technology of Artificial Intelligence in 2017.