基本信息
浏览量:110
![](https://originalfileserver.aminer.cn/sys/aminer/icon/show-trajectory.png)
个人简介
I am focusing on multi-modal generation.
My research interests span the areas of computer vision and machine learning. My PhD research was centered on efficient learning for scene understanding. This involved devising methods to reduce the amount of data, labels, and model parameters needed to effectively train machine learning models for scene understanding.
Machine learning (ML) applications require huge foundation models trained on vast data and labels. My research focuses on improving the efficiency of model parameters, data, and label annotations in training of large-scale machine learning models. Beyond these, I also worked on efficient and robust inference, which exploits communication techniques to exchange information across different ML models.
My research interests span the areas of computer vision and machine learning. My PhD research was centered on efficient learning for scene understanding. This involved devising methods to reduce the amount of data, labels, and model parameters needed to effectively train machine learning models for scene understanding.
Machine learning (ML) applications require huge foundation models trained on vast data and labels. My research focuses on improving the efficiency of model parameters, data, and label annotations in training of large-scale machine learning models. Beyond these, I also worked on efficient and robust inference, which exploits communication techniques to exchange information across different ML models.
研究兴趣
论文共 28 篇作者统计合作学者相似作者
按年份排序按引用量排序主题筛选期刊级别筛选合作者筛选合作机构筛选
时间
引用量
主题
期刊级别
合作者
合作机构
ICLR 2023 (2023)
引用0浏览0引用
0
0
arXiv (Cornell University) (2023): 1009-1019
CVPR 2023 (2023): 7836-7845
IEEE Conference on Computer Vision and Pattern Recognitionno. 1 (2022): 7571-7580
arXiv (Cornell University) (2022)
2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2022)
ICLR (2021): 9809-9818
加载更多
作者统计
合作学者
合作机构
D-Core
- 合作者
- 学生
- 导师
数据免责声明
页面数据均来自互联网公开来源、合作出版商和通过AI技术自动分析结果,我们不对页面数据的有效性、准确性、正确性、可靠性、完整性和及时性做出任何承诺和保证。若有疑问,可以通过电子邮件方式联系我们:report@aminer.cn