Zobrazeno 1 - 4
of 4
pro vyhledávání: '"Rege, Aniket"'
Large foundation models pretrained on raw web-scale data are not readily deployable without additional step of extensive alignment to human preferences. Such alignment is typically done by collecting large amounts of pairwise comparisons from humans
Externí odkaz:
http://arxiv.org/abs/2406.08469
Autor:
Rege, Aniket, Kusupati, Aditya, S, Sharan Ranjit, Fan, Alan, Cao, Qingqing, Kakade, Sham, Jain, Prateek, Farhadi, Ali
Web-scale search systems learn an encoder to embed a given query which is then hooked into an approximate nearest neighbor search (ANNS) pipeline to retrieve similar data points. To accurately capture tail queries and data points, learned representat
Externí odkaz:
http://arxiv.org/abs/2305.19435
Autor:
Kusupati, Aditya, Bhatt, Gantavya, Rege, Aniket, Wallingford, Matthew, Sinha, Aditya, Ramanujan, Vivek, Howard-Snyder, William, Chen, Kaifeng, Kakade, Sham, Jain, Prateek, Farhadi, Ali
Learned representations are a central component in modern ML systems, serving a multitude of downstream tasks. When training such representations, it is often the case that computational and statistical constraints for each downstream task are unknow
Externí odkaz:
http://arxiv.org/abs/2205.13147
Ever-increasing smartphone-generated video content demands intelligent techniques to edit and enhance videos on power-constrained devices. Most of the best performing algorithms for video understanding tasks like action recognition, localization, etc
Externí odkaz:
http://arxiv.org/abs/2110.01015