Layer normalization has demonstrated remarkable effectiveness at preventing plasticity loss in continual and reinforcement learning (RL), though the precise reasons for this effectiveness remain mysterious.

Recent studies have shown promising results on utilizing large pre-trained image-language models for video question answering.

In image classification, it is common to utilize a pretrained model to extract meaningful features of the input images, and then to train a classifier on top of it to make predictions for any downstream task.

Here, we present the VCL Benchmark: the first large-scale dataset for benchmarking SSL algorithms in rodents.

In many real-world scenarios, sequential data are time-series sampled from some underlying continuous-time process, so datasets consist of long, irregularly sampled sequences of varied lengths.

We study offline model-based optimization to maximize a black-box objective function with a static dataset of designs and scores.