🏢 Google

A-Harmonic reward function and Reward Preference Optimization (RPO) improve subject-driven text-to-image generation by enabling faster training and state-of-the-art results with a simpler setup.

This paper presents a novel neural network architecture that simultaneously learns to generate and segment images in an unsupervised manner, achieving accurate results across multiple datasets without…

Fast approximation of Minimum Bayes Risk (MBR) decoding achieved using low-rank matrix completion algorithms, drastically reducing computational cost without sacrificing translation quality.

Differentially private set representations achieve optimal privacy-utility tradeoffs with exponentially smaller error than prior histogram methods.

Transformers can now perform self-alignment, enabling simpler, faster speech recognition models.