Distilling step-by-step: Outperforming larger language models with less training data and smaller model sizes

Favorite Posted by Cheng-Yu Hsieh, Student Researcher, and Chen-Yu Lee, Research Scientist, Cloud AI Team Large language models (LLMs) have enabled a new data-efficient learning paradigm wherein they can be used to solve unseen new tasks via zero-shot or few-shot prompting. However, LLMs are challenging to deploy for real-world applications

Read More
Shared by Google AI Technology September 21, 2023

MediaPipe FaceStylizer: On-device real-time few-shot face stylization

Favorite Posted by Haolin Jia, Software Engineer, and Qifei Wang, Senior Software Engineer, Core ML In recent years, we have witnessed rising interest across consumers and researchers in integrated augmented reality (AR) experiences using real-time face feature generation and editing functions in mobile applications, including short videos, virtual reality, and

Read More
Shared by Google AI Technology September 15, 2023

On-device content distillation with graph neural networks

Favorite Posted by Gabriel Barcik and Duc-Hieu Tran, Research Engineers, Google Research In today’s digital age, smartphones and desktop web browsers serve as the primary tools for accessing news and information. However, the proliferation of website clutter — encompassing complex layouts, navigation elements, and extraneous links — significantly impairs both

Read More
Shared by Google AI Technology September 14, 2023

World scale inverse reinforcement learning in Google Maps

Favorite Posted by Matt Barnes, Software Engineer, Google Research Routing in Google Maps remains one of our most helpful and frequently used features. Determining the best route from A to B requires making complex trade-offs between factors including the estimated time of arrival (ETA), tolls, directness, surface conditions (e.g., paved,

Read More
Shared by Google AI Technology September 12, 2023

Differentially private median and more

Favorite Posted by Edith Cohen and Uri Stemmer, Research Scientists, Google Research Differential privacy (DP) is a rigorous mathematical definition of privacy. DP algorithms are randomized to protect user data by ensuring that the probability of any particular output is nearly unchanged when a data point is added or removed.

Read More
Shared by Google AI Technology September 8, 2023