Gemini: A Family of Highly Capable Multimodal Models

Gemini Robotics Team, Rohan Anil, Sebastian Borgeaud, +741

arXiv (Cornell University)

Artificial IntelligenceNatural Language ProcessingNew FamilyLarge Ai ModelImage Analysis +13

Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shift

Yaniv Ovadia, Emily Fertig, Jie Ren, +6

arXiv (Cornell University)

Dataset ShiftMachine LearningEngineeringMachine Learning ToolUncertain Data +22

Underspecification Presents Challenges for Credibility in Modern Machine Learning

Alexander D’Amour, Katherine Heller, Dan Moldovan, +37

arXiv (Cornell University)

Artificial IntelligenceEngineeringMachine LearningModern Ml PipelinesMachine Learning Tool +15

Can you trust your model's uncertainty? Evaluating predictive uncertainty under dataset shift

Yaniv Ovadia, Emily Fertig, Jie Ren, +6

arXiv (Cornell University)

Dataset ShiftMachine LearningEngineeringMachine Learning ToolUncertain Data +22

On Empirical Comparisons of Optimizers for Deep Learning

Dami Choi, Christopher J. Shallue, Zachary Nado, +3

arXiv (Cornell University)

Artificial IntelligenceHyperparameter Search SpaceHyperparameter EstimationEngineeringMachine Learning +10

PaLM 2 Technical Report

Rohan Anil, Andrew M. Dai, Melvin Johnson, +123

arXiv (Cornell University)

Artificial IntelligenceLlm Fine-tuningEngineeringMachine LearningEducation +18

Evaluating Prediction-Time Batch Normalization for Robustness under Covariate Shift

Zachary Nado, Shreyas Padhy, D. Sculley, +3

arXiv (Cornell University)

Convolutional Neural NetworkDataset ShiftMachine LearningEngineeringAutoencoders +19

Plex: Towards Reliability using Pretrained Large Model Extensions

Dustin Tran, Jeremiah Liu, Michael W. Dusenberry, +23

arXiv (Cornell University)

Artificial IntelligenceFew-shot LearningEngineeringMachine LearningSoftware Analysis +22

Uncertainty Baselines: Benchmarks for Uncertainty & Robustness in Deep Learning

Zachary Nado, Neil Band, Mark Collier, +21

arXiv (Cornell University)

Revisiting One-vs-All Classifiers for Predictive Uncertainty and\n Out-of-Distribution Detection in Neural Networks

Shreyas Padhy, Zachary Nado, Jie Ren, +3

arXiv (Cornell University)