人才培养

博士成员介绍(部分)

2020级

姓名:赵娟
教育背景:2020级 博士 在读
联系方式:Zhaojuan1@stu.scu.edu.cn

研究兴趣:
神经网络中的小样本学习

研究成果:

  • Juan Z , Lili K, Jiancheng L. An Overview of Deep Neural Networks for Few-Shot Learning[J].Big Data Mining and Analytics, 2024.10.26599/BDMA.2024.9020049.
  • Juan Z et al. “Enhancing Few Shot Distribution Estimation by Mitigating Negative Calibration Effects,” in IEEE Transactions on Circuits and Systems for Video Technology.

姓名:薛明峰
教育背景:2020级 博士 在读
联系方式:mingfengxue@outlook.com
个人主页:https://scholar.google.com/citations?view_op=list_works&hl=zh-CN&user=gRXSf3sAAAAJ

研究兴趣:
大模型预训练,大模型数学

研究成果:

  • Mingfeng Xue, Dayiheng Liu, Wenqiang Lei, Xingzhang Ren, Baosong Yang, Jun Xie, Yidan Zhang, Dezhong Peng, Jiancheng Lv: Dynamic Voting for Efficient Reasoning in Large Language Models. EMNLP (Findings) 2023.
  • Mingfeng Xue, Dayiheng Liu, Wenqiang Lei, Jie Fu, Jian Lan, Mei Li, Baosong Yang, Jun Xie, Yidan Zhang, Dezhong Peng, Jiancheng Lv: Unifying Discrete and Continuous Representations for Unsupervised Paraphrase Generation. EMNLP 2023.

2021级

姓名:黄幼成
教育背景:2021级 博士 在读

研究兴趣:
语言/多模态大模型的对齐和安全

研究成果:

  • Reconciliation of pre-trained models and prototypical neural networks in few-shot named entity recognition
    (https://aclanthology.org/2022.findings-emnlp.129/)

姓名:俞蔡阳
教育背景:2021级 博士 在读
联系方式:yucy324@gmail.com
个人主页:https://scholar.google.com/citations?user=YISjXPwAAAAJ&hl=en
毕业去向:

研究兴趣:
神经架构搜索(NAS),AI for Science

研究成果:

姓名:王坚
教育背景:2021级 博士 在读
联系方式:jianwang.scu@gmail.com
个人主页:https://scholar.google.com/citations?user=Irn-tV4AAAAJ&hl=en

研究兴趣:
计算机视觉、生成模型、医学图像

研究成果:

  • CR-GAN: Automatic Craniofacial Reconstruction for Personal Identification, PR 2022
  • Shunting at Arbitrary Feature Levels via Spatial Disentanglement: Toward Selective Image Translation, IEEE TNNLS 2023
  • MS3D: A RG Flow-Based Regularization for GAN Training with Limited Data, ICML 2024
  • 2022昇腾AI创新大赛 应用赛道初创创新赛道银奖 RoboMaster 2022 University AI Challenge 三等奖

姓名:黄晨
教育背景:2021级 博士 在读
联系方式:huangc.scu@gmail.com
个人主页:https://scholar.google.com/citations?user=acAfKhEAAAAJ&hl=zh-CN

研究兴趣:
对话式人工智能,人机交互

研究成果:

  • Chen Huang, Yiping Jin, Ilija Ilievski, Wenqiang Lei, Jiancheng Lv. ARAIDA: Analogical Reasoning-Augmented Interactive Data Annotation, The the 62nd Annual Meeting of the Association for Computational Linguistics (ACL, CCF-A). 2024, Accepted
  • Chen Huang, Haoyang Li, Yifan Zhang, Wenqiang Lei, Jiancheng Lv. Cross-Space Adaptive Filter: Integrating Graph Topology and Node Attributes for Alleviating the Over-smoothing Problem, Proceedings of the ACM on Web Conference (WWW, CCF-A). 2024: 803–814
  • Chen Huang, Peixin Qin, Wenqiang Lei, Jiancheng Lv. Towards Equipping Transformer with the Ability of Systematic Compositionality, Proceedings of the AAAI Conference on Artificial Intelligence (AAAI, CCF-A). 2023:18289-18297
  • Chen Huang, Peixin Qin, Wenqiang Lei, Jiancheng Lv. Reduce Human Labor On Evaluating Conversational Information Retrieval System: A Human-Machine Collaboration Approach, The 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP, CCF-B). 2023: 10876-10891
  • Chen Huang, Liangxu Pan, Qinli Yang, Hongliang Wang, and Junming Shao. Flexible, Robust, Scalable Semi-supervised Learning via Reliability Propagation, In 21th IEEE International Conference on Data Mining (ICDM, CCF-B).2021: 200-209.

2022级

姓名:邬鸿杰
教育背景:2022级 博士 在读
联系方式:wuhongjie0818@gmail.com
个人主页:https://hongjie-wu.pages.dev/

研究兴趣:
深度学习,生成模型

研究成果:

  • Diffusion Posterior Proximal Sampling for Image Restoration (ACM MM 2024 Oral)
  • Multi-view subspace clustering on topological manifold (NeurIPS 2022 Spotlight)
  • Pure graph-guided multi-view subspace clustering (Pattern Recognition 2023)

姓名:孔莉莉
教育背景:2022级 博士 在读
联系方式:kongllscu@126.com

研究兴趣:
small data learning, few-shot learning, neural network

研究成果:

  • ELSA: Equivariant Self-Supervised Adaptation for
    Small Data Learning.
  • An Overview of Deep Neural Networks for Few-Shot Learning
  • Scaling Laws for Small Data Distribution.

姓名:周宇浩
教育背景:2022级 直博 在读
联系方式:sooptq@gmail.com
个人主页:https://scholar.google.com/citations?user=bGKF2tUAAAAJ&hl=en

研究兴趣:
边缘计算,带隐私保护的机器学习,分布式模型训练

研究成果:

  • Zhou, Y., Shi, M., Li, Y., Sun, Y., Ye, Q., & Lv, J. (2023). Communication-efficient federated learning with single-step synthetic features compressor for faster convergence. In Proceedings of the IEEE/CVF International Conference on Computer Vision (pp. 5031-5040).
  • Zhou, Y., Shi, M., Tian, Y., Ye, Q., & Lv, J. (2024). DeFTA: A plug-and-play peer-to-peer decentralized federated learning framework. Information Sciences, 670, 120582.
  • Zhou, Y., Shi, M., Tian, Y., Li, Y., Ye, Q., & Lv, J. (2024, April). Federated CINN Clustering for Accurate Clustered Federated Learning. In ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 5590-5594). IEEE.
  • Shi, M., Zhou, Y., Wang, K., Zhang, H., Huang, S., Ye, Q., & Lv, J. (2024). PRIOR: Personalized Prior for Reactivating the Information Overlooked in Federated Learning. Advances in Neural Information Processing Systems, 36.

姓名:张瀚文
教育背景:2022级 直博 在读
联系方式:hanwenzhang@stu.scu.edu.cn

研究兴趣:
分子设计,生成模型

研究成果:

  • AlphaPharm: a reinforcement-active learning framework to streamline lead optimization in drug discovery
  • MolEM: An EM Approach to Learning Generative Orders for Molecular Graphs
  • 2023上海国际计算生物学创新大赛—药物筛选AI算法“凌越”挑战赛

2023级

姓名:牛超群
教育背景:2023级 博士 在读
联系方式:chelton.niu@gmail.com

研究兴趣:
计算机视觉,生成模型,医学图像

研究成果:

  • Neural Boneprint: Person Identification from Bones Using Generative Contrastive Deep Learning. ACM MM 2024 (Oral).
  • Multi-view Adaptive Bone Activation from Chest X-Ray with Conditional Adversarial Nets. MMM 2023.
  • A fully automated sex estimation for proximal femur X-ray images through deep learning detection and classification. Legal Medicine, 2022.
  • 2022昇腾AI创新大赛 应用赛道初创创新赛道银奖

姓名:郑文豪
教育背景:2023级 直博 在读
联系方式:zhengwenhao@stu.scu.edu.cn

研究兴趣:
检索增强生成

研究成果:

  • ProtoDiff: Prototypical Diffusion Model for Few-Shot Molecular Image Generation, BIBM 2024 under review.

姓名:李书剑
教育背景:2023级 博士 在读
2018级 硕士 华中科技大学
2014级 学士 华中科技大学
联系方式:shujianli96@163.com

研究兴趣:
核电反应堆关键设备智能诊断与健康管理,人工智能技术在核电领域的应用

研究成果:

  • S. Li, T. Pang and T. Yang, “A Data File Encoding Method Applicable to Condition Monitoring System of Nuclear Power Plant,” 2023 8th Asia Conference on Power and Electrical Engineering (ACPEE), Tianjin, China, 2023, pp. 1239-1243.
  • 李书剑,庞天枫,杨泰波,等.反应堆关键设备状态数据标准化研究[J].计算机测量与控制, 2023, 31(6):198-203.
  • “华为杯”第十六届中国研究生数学建模竞赛全国一等奖

2024级

姓名:杨嘉铭
教育背景:2024级 博士 在读
联系方式:macixcn@gmail.com
个人主页:jiamingyy.github.io

研究兴趣:
Model Compression, On device Training

研究成果:

  • Yang J, Tang C, Yu C, et al. GWQ: Group-Wise Quantization Framework for Neural  Networks[C]//Asian Conference on Machine Learning. PMLR, 2024: 1526-1541.

姓名:何雨声
教育背景:2024级 博士 在读
联系方式:1046477352@qq.com

研究兴趣:
小样本图像分类,目标检测

研究成果:
暂无

上一篇:
下一篇: