Skip to main content

Archive

RO-ViT: Region-aware pre-training for open-vocabulary object detection with vision transformers

Responsible AI at Google Research: Perception Fairness

How to compare a noisy quantum processor to a classical computer

Teaching language models to reason algorithmically

Language to rewards for robotic skill synthesis

Google at Interspeech 2023

Autonomous visual information seeking with large language models

Neural network pruning with combinatorial optimization

STUDY: Socially aware temporally causal decoder recommender systems

Advances in document understanding

AdaTape: Foundation model with adaptive computation and dynamic read-and-write