Li Fei-Fei

TL;DR: MentorNet as discussed by the authors provides a data-driven curriculum (sample weighting scheme) for StudentNet to focus on the sample the label of which is probably correct during training.

TL;DR: It is shown that the data obtained through RoboTurk enables policy learning on multi-step manipulation tasks with sparse rewards and that using larger quantities of demonstrations during policy learning provides benefits in terms of both learning consistency and final performance.

TL;DR: The hypothesis that scene categories reflect functions, or the possibilities for actions within a scene, is tested, suggesting instead that a scene's category may be determined by the scene's function.

TL;DR: It is shown that object sensitivity in PPA also has an anterior-posterior gradient, with stronger responses to abstract objects in posterior PPA, casting doubt on the traditional view of PPA as a single coherent region and suggesting that PPA is composed of one subregion specialized for the processing of low-level visual features and object shape, and a separate subregion more involved in memory and scene context.

TL;DR: The authors provides a thorough account of the opportunities and risks of foundation models, ranging from their capabilities (e.g., language, vision, robotics, reasoning, human interaction) and technical principles(e. g.g. model architectures, training procedures, data, systems, security, evaluation, theory) to their applications.