L
Li Fei-Fei
Researcher at Stanford University
Publications - 515
Citations - 199224
Li Fei-Fei is an academic researcher from Stanford University. The author has contributed to research in topics: Computer science & Medicine. The author has an hindex of 120, co-authored 420 publications receiving 145574 citations. Previous affiliations of Li Fei-Fei include Google & California Institute of Technology.
Papers
More filters
Journal ArticleDOI
Preparation of Zn−Gly and Se−Gly and Their Effects on the Nutritional Quality of Tea (Camellia sinensis)
TL;DR: In this article , the effects of Zn−Gly and Se-Gly on tea plants were determined, and the results suggest that combined application of both Zn and Se was more effective than single Zn or Se alone.
Journal ArticleDOI
Author Correction: Advances, challenges and opportunities in creating data for trustworthy AI
Posted Content
SURREAL-System: Fully-Integrated Stack for Distributed Deep Reinforcement Learning.
Linxi Fan,Yuke Zhu,Jiren Zhu,Zihua Liu,Orien Zeng,Anchit Gupta,Joan Creus-Costa,Silvio Savarese,Li Fei-Fei +8 more
TL;DR: The learning performances of the SURREAL algorithms establish new state-of-the-art on OpenAI Gym and Robotics Suites tasks and can easily scale to 1000s of CPU cores and 100s of GPUs.
Posted Content
Physion: Evaluating Physical Prediction from Vision in Humans and Machines
Daniel M. Bear,Elias Wang,Damian Mrowca,Felix J. Binder,Hsiau-Yu Fish Tung,R. T. Pramod,Cameron Holdaway,Sirui Tao,Kevin A. Smith,Fan-Yun Sun,Li Fei-Fei,Nancy Kanwisher,Joshua B. Tenenbaum,Daniel L. K. Yamins,Judith E. Fan +14 more
TL;DR: In this paper, the authors present a visual and physical prediction benchmark that precisely measures the capability of machine learning algorithms to make predictions about commonplace real world physical events, including rigid and soft-body collisions, stable multi-object configurations, rolling and sliding, and projectile motion.
Journal ArticleDOI
Active Task Randomization: Learning Visuomotor Skills for Sequential Manipulation by Proposing Feasible and Novel Tasks
TL;DR: Active Task Randomization (ATR) as discussed by the authors is an approach that learns visuomotor skills for sequential manipulation by automatically creating feasible and novel tasks in simulation, during training, the approach procedurally generates tasks using a graph-based task parameterization.