Wei Li

Wei Li

I am a Ph.D. student in the College of Computer Science at Zhejiang University of Technology, working with Prof. Chunhua Shen (沈春华)’s team under the supervision of Prof. Jianwei Zheng (郑建炜). I expect to graduate in June 2028.

I am currently seeking long-term internship opportunities through graduation, with a focus on multimodal large models.

📝 Publications

ICML 2026
Latent Spectral Operators pipeline

Solving Spatial-Spectral Fusion with Latent Spectral Operators

Wei Li, Jieyuan Pei, Junnan Xu, Xuanfeng Ding, Junwei Zhu, Wanjun Chen, Jianwei Zheng

Project / Code / Dataset

  • Wei Li, Jiawei Jiang, Jie Wu, Kaihao Yu, Jianwei Zheng*. LMO: Linear Mamba Operator for MRI Reconstruction. In The Conference on Computer Vision and Pattern Recognition, 2025. (CVPR 2025, 2025-2-26, 医学图像)
  • Wei Li, Junwei Zhu, Honghui Xu, Jiawei Jiang, Jianwei Zheng*. SpecSolver: Solving Spatial-Spectral Fusion via Semantic Transformer. ACM Multimedia 2025. (ACMMM 2025, 2025-7-5, 图像融合)
  • Jianwei Zheng, Wei Li, Ni Xu, Junwei Zhu, Xuxiao Lin, Xiaoqin Zhang*. Alias-Free Mamba Neural Operator. In The Thirty-eighth Annual Conference on Neural Information Processing Systems, 2024. (NeurIPS 2024, 学生一作, 2024-9-26, 偏微分方程)
  • Wei Li, Honghui Xu, Yueqian Quan, Zhe Chen, Jianwei Zheng*. Arbitrary-Scale Spatial-Spectral Fusion using Kernel Integral and Progressive Resampling. (Information Fusion 2026, 2026-1-8, 图像融合, IF:15.5, 中科院1区Top)
  • Wei Li, Jiawei Jiang, Ni Xu, Ying Cui, Yan Li*, Jianwei Zheng*. Spatial-Spectral Fusion Neural Operator. IEEE International Conference on Multimedia & Expo (ICME), 2025. (ICME 2025, 2025-3-18, 图像融合)
  • Jiawei Jiang, Wei Li, Jieyuan Pei, Junwei Zhu, Honghui Xu, Yuchao Feng, Jianwei Zheng. S²TA-Fuse: Semantic-Superpixel Tokenized Attention for Spatial Spectral Fusion. (TGRS 2026, 共一第二, 2026-1-19, 图像融合, 中科院1区Top)
  • 郑建炜, 李卫, 严亦东, 徐妮, 余凯豪. 一种基于神经算子和渐进重采样的光谱图像融合方法。(专利授权, CN118735805A[P], 2024-10-01).

Honors and Awards

  • 2025年中国科协青年人才托举工程博士生专项计划
  • 2025年博士国家奖学金
  • 2025年浙江工业大学学术之星

Educations

  • 2019.09 - 2023.06, Undergraduate, Zhejiang University of Technology, Computer Science and Technology + Intelligent Science and Technology, double major; CPC member.
  • 2023.09 - 2025.06, M.S., Zhejiang University of Technology, Computer Science and Technology (081200); GPA and comprehensive evaluation ranked in the top 1%.
  • 2025.09 - Present, Ph.D., Zhejiang University of Technology, Computer Science and Technology (081200).

Internships

2026.03.09 - Present, 阿里巴巴虎鲸文娱, 视频渲染去噪

  • 蒙特卡洛采样渲染成像会产生长尾分布噪声，从成像角度出发，利用成像时的统计量解决视频渲染时出现的噪声及伪影。预计投稿 AAAI。

2025.08.04 - 2026.02.04, 同花顺AIGC算法部门, 图像编辑 & 理解与生成编辑统一模型

  • FreeEraser: Mask-Free Object Removal via Attention Regularization. (ECCV 在审，初始分数 442)
  • 利用 NanoBanana 构建数据集，LoRA 微调 Flux-Kontext 模型用于图像擦除。图像编辑
  • LongCat, Qwen-image, Qwen-vl, Flux-Kontext, Flux-fill, 理解与生成统一模型