Announcing the first Machine Unlearning Challenge
On-device diffusion plugins for conditioned text-to-image generation
Unifying image-caption and image-classification datasets with prefix conditioning
Preference learning with automated feedback for cache eviction
SoundStorm: Efficient parallel audio generation
Responsible AI at Google Research: AI for Social Good
The world’s first braiding of non-Abelian anyons
Google at CVPR 2023
Speed is all you need: On-device acceleration of large diffusion models via GPU-aware optimizations
Reconstructing indoor spaces with NeRF
Enabling delightful user experiences via predictive models of human attention
Imagen Editor and EditBench: Advancing and evaluating text-guided image inpainting
Evaluating speech synthesis in many languages with SQuId
Visual captions: Using large language models to augment video conferences with dynamic visuals
AVFormer: Injecting vision into frozen speech models for zero-shot AV-ASR
Retrieval-augmented visual-language pre-training
