I am Wei Li, a principal research scientist at Huawei Foundation Model Department. Currently, I am leading the Multimodal Generation Post-Training team. My research interests broadly encompass LLM efficiency and multimodal generation, and reinforcement learning.

I received my M.S. degree from Tsinghua University in 2019, co-advised by Prof. Guoqiang Bai and IEEE Fellow Prof. Zhihua Wang. Since joining Huawei in 2019, I have collaborated closely with Mr.Jie Hu, Dr.Hanting Chen and Dr.Yunhe Wang

Driven by a passion for bridging cutting-edge algorithms with strict hardware constraints, I have pioneered multiple core technologies that empower intelligent imaging and generative models across tens of millions of flagship devices globally (Huawei Pura/Mate Series Phones, MatePad etc.) . I have published over 20 papers in top-tier AI venues (including multiple ICLR Spotlight, CVPR, ICML, ACL, ECCV, NeurIPS, and IEEE TIP articles) and hold more than 30 patents.

🤝 Join Our Team / Hiring Interns

We are actively seeking self-motivated interns to work on next-generation multimodal generation systems. If you are passionate about defining the future of ubiquitous generative AI and publishing at top-tier venues, please feel free to drop me an email with your CV.

🚀 News

===========
[2026.07] Two paper accepted by ACMMM 2026 (DSPO, RadAR).
[2026.06] One paper accepted by ECCV 2026 (AlloSR).
[2026.06] Honored to serve as a Virtual Session Chair for the [LLM Efficiency] track at ACL 2026.
[2026.05] Three papers accepted by ICML 2026 (ES-COT, CSD, Extra-CoT).
[2026.04] One paper accepted by ACL 2026 (Dac-KL).
[2025.11] One paper accepted by IEEE TIP (Hi-Mamba).
[2025.05] One paper accepted by IEEE TIP. (LIPT).
[2025.01] One paper accepted by CVPR 2025.
[2025.01] Three papers accepted by ICLR 2025, including 2 Spotlight(CBQ, MipKD), and AugKD！
[2024.11] Two papers accepted by AAAI 2025 (GIM, DCKD).
[2024.07] One paper accepted by ECCV 2024 (PQ-SAM).
[2024.02] One paper accepted by CVPR 2024 (SAM4IR).
[2023.09] One paper accepted by NeurIPS 2024 (Genimage).
[2023.04] Won the Winner Award in NTIRE Challenge on Image Denoising@CVPR2023.
[2023.02] One paper accepted by CVPR 2023 (RefSR-NeRF).
[2021.11] One paper accepted by AAAI 2022 (OoDHDR-codec).

Selected Publications

Knowledge distillation with multi-granularity mixture of priors for image super-resolution

Simiao Li, Yun Zhang, Wei Li^†, Hanting Chen, Wenjia Wang, Bingyi Jing, Shaohui Lin, Jie Hu

^†Project Leader & Co-first author, ICLR 2025 (Spotlight)   [Paper]   [BibTeX]

@inproceedings{li2025knowledge, title={Knowledge distillation with multi-granularity mixture of priors for image super-resolution}, author={Li, Simiao and Zhang, Yun and Li, Wei and Chen, Hanting and Wang, Wenjia and Jing, Bingyi and Lin, Shaohui and Hu, Jie}, booktitle={The Thirteenth International Conference on Learning Representations}, year={2025} }

LIPT: Latency-Aware Image Processing Transformer

Junbo Qiao, Wei Li^†, Haizhen Xie, Hanting Chen, Jie Hu, Shaohui Lin, Jungong Han

^†Project Leader & Co-first author, IEEE TIP 2025   [Paper]   [Code]   [BibTeX]

@article{qiao2025lipt, title={LIPT: Latency-Aware Image Processing Transformer}, author={Qiao, Junbo and Li, Wei and Xie, Haizhen and Chen, Hanting and Hu, Jie and Lin, Shaohui and Han, Jungong}, journal={IEEE Transactions on Image Processing}, year={2025} }

AugKD: Ingenious Augmentations Empower Knowledge Distillation for Image Super-Resolution

Yun Zhang, Wei Li^†, Simiao Li, Hanting Chen, Zhijun Tu, Wenjia Wang, Bingyi Jing, Shaohui Lin, Jie Hu

^†Project Leader & Co-first author, ICLR 2025   [Paper]   [BibTeX]

@inproceedings{zhang2025augkd, title={AugKD: Ingenious Augmentations Empower Knowledge Distillation for Image Super-Resolution}, author={Zhang, Yun and Li, Wei and Li, Simiao and Chen, Hanting and Tu, Zhijun and Wang, Wenjia and Jing, Bingyi and Lin, Shaohui and Hu, Jie}, booktitle={The Thirteenth International Conference on Learning Representations}, year={2025} }

RefSR-NeRF: Towards High Fidelity and Super Resolution View Synthesis

Xudong Huang, Wei Li^†, Jie Hu, Hanting Chen, Yunhe Wang

^†Project Leader & Co-first author, CVPR 2023   [Paper]   [BibTeX]

@inproceedings{huang2023refsr, title={RefSR-NeRF: Towards High Fidelity and Super Resolution View Synthesis}, author={Huang, Xudong and Li, Wei and Hu, Jie and Chen, Hanting and Wang, Yunhe}, booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year={2023} }

RDDM: Practicing Raw Domain Diffusion Model for Real-World Image Restoration

Yan Chen, Yi Wen, Wei Li^†, Junchao Liu, Yong Guo, Jie Hu, Xinghao Chen

^†Project Leader, Arxiv 2025   [Paper]   [BibTeX]

@article{chen2025rddm, title={RDDM: Practicing Raw Domain Diffusion Model for Real-World Image Restoration}, author={Chen, Yan and Wen, Yi and Li, Wei and Liu, Junchao and Guo, Yong and Hu, Jie and Chen, Xinghao}, journal={arXiv preprint}, year={2025} }

CBQ: Cross-Block Quantization for Large Language Models

Xin Ding, Xiaoyu Liu, Zhijun Tu, Yun Zhang, Wei Li^†, Jie Hu, Hanting Chen, Yehui Tang, Zhiwei Xiong, Baoqun Yin, Yunhe Wang

^†ICLR 2025 (Spotlight)   [Paper]   [BibTeX]

@inproceedings{ding2025cbq, title={CBQ: Cross-Block Quantization for Large Language Models}, author={Ding, Xin and Liu, Xiaoyu and Tu, Zhijun and Zhang, Yun and Li, Wei and Hu, Jie and Chen, Hanting and Tang, Yehui and Xiong, Zhiwei and Yin, Baoqun and Wang, Yunhe}, booktitle={The Thirteenth International Conference on Learning Representations}, year={2025} }