Publications

*: Equal contribution or alphabetic ordering.

Conference Papers

  1. AugKD: Ingenious Augmentations Empower Knowledge Distillation for Image Super-Resolution (Poster)
    Yun Zhang*, Wei Li*, Simiao Li, Hanting Chen, Zhijun Tu, Bingyi Jing, Shaohui Lin, Jie Hu, Wenjia Wang
    International Conference on Learning Representations (ICLR), 2025.

  2. Knowledge Distillation with Multi-granularity Mixture of Priors for Image Super-Resolution (Spotlight)
    Simiao Li*, Yun Zhang*, Wei Li, Hanting Chen, Wenjia Wang, Bingyi Jing, Shaohui Lin, Jie Hu
    International Conference on Learning Representations (ICLR), 2025.

  3. CBQ: Cross-Block Quantization for Large Language Models (Spotlight)
    Xin Ding, Xiaoyu Liu, Yun Zhang, Zhijun Tu, Wei Li, Jie Hu, Hanting Chen, Yehui Tang, Zhiwei Xiong, Baoqun Yin, Yunhe Wang
    International Conference on Learning Representations (ICLR), 2025.

Preprints and Manuscripts

  1. Soft BPR Loss for Dynamic Hard Negative Sampling in Recommender Systems
    Kexin Shi, Yun Zhang, Bingyi Jing, Wenjia Wang

  2. Hop-Mix-DNS: Hop-wise Mixing Dynamic Negative Sampling for Graph Neural Network-based Recommendation Systems
    Yun Zhang, Kexin Shi, Bingyi Jing

Patents

  1. Yun Zhang, Wei Li, Simiao Li, Jie Hu, Hanting Chen, Zhijun Tu, Wenjia Wang, Yunhe Wang. (2023, September 15). CN117422131A. Model training method and training equipment.