Li Fei-Fei

TL;DR: BEHAVIOR as mentioned in this paper is a benchmark for embodied AI with 100 activities in simulation, spanning a range of everyday household chores such as cleaning, maintenance, and food preparation, aiming to reproduce the challenges that agents must face in the real world.

TL;DR: This paper assessed the contributions of multiple properties to scene representation by partitioning the variance explained in human behavioral and brain measurements by three feature models whose inter-correlations were minimized a priori through stimulus preselection.

TL;DR: OPTIMOL (a framework for Online Picture collection via Incremental MOdel Learning) is a novel, automatic dataset collecting and model learning system for object categorization that mimics the human learning process in such a way that the more confident data you incorporate in the training data, the more reliahle models can be learnt.

TL;DR: In this article , protein tyrosine phosphatase receptor-type O (PTPRO) is used to suppress the metastasis of esophageal squamous cell carcinoma (ESCC).

TL;DR: In this article, the authors demonstrate that Transformers are fairly robust to distribution shifts and hence improve federated learning over heterogeneous data and conduct the first rigorous empirical investigation of different neural architectures across a range of federated algorithms, real-world benchmarks, and heterogenous data splits.