## 自我介绍

  徐聪

本科院校: 烟台大学

毕业院校: 华东师范大学

指导老师: 王骏教授、张伟教授

研究方向: 机器学习

研究领域: 优化算法/推荐系统

科研成果: 4 CCF-A & 2 一区 Top

所获荣誉: 国家奖学金、上海市优秀毕业生

主要科研成果

 

  • Cong Xu, Jun Wang, Jianyong Wang, Wei Zhang. Graph-enhanced Optimizers for Structure-aware Recommendation Embedding Evolution. NeurIPS, 2024. (CCF-A)
  • Cong Xu, Yunhang He, Jun Wang, Wei Zhang. STAIR: Manipulating Collaborative and Multimodal Information for E-Commerce Recommendation. AAAI, 2025. (CCF-A)
  • Cong Xu, Jun Wang, Wei Zhang. StableGCN: Decoupling and Reconciling Information Propagation for Collaborative Filtering. TKDE, 2023. (CCF-A, 一区 Top)
  • Yunhang He, Cong Xu, Jun Wang, Wei Zhang. Collaborative Filtering Meets Spectrum Shift: Connecting User-Item Interaction with Graph-Structured Side Information. KDD, 2025. (CCF-A, 共一)
  • Cong Xu, Wei Zhang, Jun Wang, Min Yang. Understanding Adversarial Robustness From Feature Maps of Convolutional Layers. TNNLS, 2024. (CCF-B, 一区 Top)
  • Cong Xu, Xiang Li, Min Yang. An Orthogonal Classifier for Improving the Adversarial Robustness of Neural Networks. Inf. Sci., 2022. (一区 Top)
  • Cong Xu, Wenbin Liang, Mo Yu, Anan Liu, et al. Pushing the Limits of Low-Bit Optimizers: A Focus on EMA Dynamics. TPAMI, 2026. (CCF-A, Major Revision)
  • Kun Ma, Cong Xu, Zeyuan Chen, Wei Zhang. Pattern-Wise Transparent Sequential Recommendation. TKDE, 2025. (CCF-A, 一区 Top)

低精度优化器 (Low-bit Optimizer)

  • 低精度"动量"状态维护: ️✅内存友好 ✅精度保持

Cong Xu, et al. Pushing the Limits of Low-Bit Optimizers: A Focus on EMA Dynamics. 2025. Submitted to TPAMI

图增强优化器 (Graph-enhanced Optimizer)

  • 图结构先验约束下降方向: ️✅高质量嵌入表示 ✅零推理成本

Cong Xu, et al. Graph-enhanced Optimizers for Structure-aware Recommendation Embedding Evolution. NeurIPS, 2024. Cong Xu, et al. STAIR: Manipulating Collaborative and Multimodal Information for E-Commerce Recommendation. AAAI, 2025.

教材编写

未来规划

  • 教学: 理论 & 实践结合的课程

  • 科研:

  • 基金: 面向生成式推荐的高效语义编码：基于扩散方程的统一视角

  • 生活: 足球、象棋、爬山…
Thanks!