杨秀隆在CCNU

华中师范大学南湖综合楼7094

华中师范大学讲师/师资博士后。博士毕业于美国佐治亚州立大学，本科厦门大学。

研究方向：深度学习技术, 如生成模型、能量模型、半/无监督学习、教育数据挖掘。

目前主要研究内容：

深度学习模型训练效率优化
生物信息学
教育大模型

news

Jan 22, 2025	获批2025年度湖北省自然科学基金青年B类（原青年项目）
Apr 05, 2024	论文 TransLNP 被中科院二区 Briefings in Bioinformatics接收！
Mar 01, 2024	入职华中师范大学计算机学院

latest posts

Dec 31, 2099	教师手机或平板控制电脑，当翻页笔用甚至写字
Feb 02, 2025	docker GPU报错
Jan 31, 2025	Ollama下载模型路径存储位置及权限
Jan 04, 2025	将HF模型转GGUF格式用于Ollama
Dec 31, 2024	硕博面试小建议——讲好故事

selected publications

CVPR CVPR CCF A 会议

Towards Bridging the Performance Gaps of Joint Energy-Based Models

Xiulong Yang, Qing Su, and Shihao Ji

In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Jun 2023

arXiv Bib PDF Code

@inproceedings{yang2023sajem,
  author = {Yang, Xiulong and Su, Qing and Ji, Shihao},
  title = {Towards Bridging the Performance Gaps of Joint Energy-Based Models},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  month = jun,
  year = {2023}
}

Your ViT is Secretly a Hybrid Discriminative-Generative Diffusion Model

Xiulong Yang, Sheng-Min Shih, Yinlin Fu, and 2 more authors

Aug 2022

Abs arXiv Bib Code

@misc{yang2022vit,
  title = {Your ViT is Secretly a Hybrid Discriminative-Generative Diffusion Model},
  author = {Yang, Xiulong and Shih, Sheng-Min and Fu, Yinlin and Zhao, Xiaoting and Ji, Shihao},
  year = {2022},
  month = aug,
  eprint = {2208.07791},
  primaryclass = {cs.CV}
}

ICCV ICCV CCF A 会议

JEM++: Improved Techniques for Training JEM

Xiulong Yang, and Shihao Ji

In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), Sep 2021

arXiv Bib PDF Code

@inproceedings{yang2021jempp,
  author = {Yang, Xiulong and Ji, Shihao},
  title = {JEM++: Improved Techniques for Training JEM},
  booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
  month = sep,
  year = {2021}
}