Month: October 2024
Pushing the frontiers of audio generation
Research Published 30 October 2024 Authors Zalán Borsos, Matt Sharifi and Marco Tagliasacchi Our pioneering speech generation technologies are helping people around the world ...
A return to hand-written notes by learning to read & write
Digital note-taking is gaining popularity, offering a durable, editable, and easily indexable way of storing notes in a vectorized form. However, a substantial gap ...
What does electrodermal sensing reveal? Insights from the Pixel Watch & Fitbit Sense 2
Applications in mental health research In our second paper, “Evidence of Differences in Diurnal Electrodermal, Temperature, and Heart Rate Patterns by Mental Health Status ...
New generative AI tools open the doors of music creation
This work was made possible by core research and engineering efforts from Andrea Agostinelli, Zalán Borsos, George Brower, Antoine Caillon, Cătălina Cangea, Noah Constant, ...
Scalable self-improvement for compiler optimization
Most systems we regularly interact with, such as computer operating systems, are faced with the challenge of providing good performance, while managing limited resources ...
Learning DeepVariant’s hidden powers
Examining DeepVariant To better understand what DeepVariant is learning from its training data, we used a set of simple clustering and visualization methods to ...
Taking medical imaging embeddings 3D
Over recent years, developers and researchers have made progress in efficiently building AI applications. Google Research has contributed to this effort by providing easy-to-use ...
Evaluating and enhancing probabilistic reasoning in language models
To understand the probabilistic reasoning capabilities of three state-of-the-art LLMs (Gemini, GPT family models), we define three distinct tasks: estimating percentiles, drawing samples, and ...
HDR photo editing with machine learning
High dynamic range (HDR) photography techniques can accurately capture a scene’s full range of brightness values — from those of its darkest shadows to ...
Validating random circuit sampling as a benchmark for measuring quantum progress
Noise disrupts quantum correlations, effectively shrinking the available quantum circuit volume. We seek to understand if it’s possible to harness the full quantum circuit ...
