基本信息
浏览量:21
![](https://originalfileserver.aminer.cn/sys/aminer/icon/show-trajectory.png)
个人简介
My research focused on making large language models cheaper to work with - via sparsity, adaptive computation and better distributed computing infrastructure.
I authored some of the pioneering work on Attention for Vision, notably training the first ever fully-attentional vision model. I proposed LambdaNetworks as a faster alternative which resulted in 4-10x speed-ups over the prior state-of-the-art. I also worked on simple baselines for image classification and video classification.
I authored some of the pioneering work on Attention for Vision, notably training the first ever fully-attentional vision model. I proposed LambdaNetworks as a faster alternative which resulted in 4-10x speed-ups over the prior state-of-the-art. I also worked on simple baselines for image classification and video classification.
研究兴趣
论文共 18 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
OpenAI,Josh Achiam,Steven Adler,Sandhini Agarwal,Lama Ahmad,Ilge Akkaya, Florencia Leoni Aleman,Diogo Almeida,Janko Altenschmidt,Sam Altman, Shyamal Anadkat, Red Avila,
CoRR (2023)
引用3099浏览0EI引用
3099
0
CoRRpp.1044-1044, (2022)
ArXiv (2021)
引用0浏览0EI引用
0
0
ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 34 (NEURIPS 2021) (2021)
引用0浏览0引用
0
0
arXivorg (2020)
引用0浏览0引用
0
0
user-5f8cf7e04c775ec6fa691c92(2020)
引用0浏览0引用
0
0
user-5bd69975530c70d56f390249(2020)
引用0浏览0引用
0
0
加载更多
作者统计
#Papers: 17
#Citation: 8327
H-Index: 10
G-Index: 17
Sociability: 6
Diversity: 0
Activity: 0
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