Scaling Vision with Sparse Mixture of Experts
Training Machine Learning Models More Efficiently with Dataset Distillation
More Efficient In-Context Learning with GLaM
General and Scalable Parallelization for Neural Networks
Decisiveness in Imitation Learning for Robots
Permutation-Invariant Neural Networks for Reinforcement Learning
MetNet-2: Deep Learning for 12-Hour Precipitation Forecasting
Making Better Future Predictions by Watching Unlabeled Videos
Practical Differentially Private Clustering
How Underspecification Presents Challenges for Machine Learning
Baselines for Uncertainty and Robustness in Deep Learning
