Presenting AVFormer, a simple method for injecting visual information into frozen speech models for zero-shot audiovisual (AV) automatic speech recognition (ASR). Read about how AVFormer achieves state-of-the-art AV-ASR performance and more → https://
goo.gle/3IU40P3
@googleai
-
AVFormer Achieves State-of-the-Art Audiovisual Speech Recognition
By
–
-
REVEAL: Retrieval-Augmented Visual-Language Model for Knowledge-Intensive Tasks
By
–
Learn how REVEAL, an end-to-end retrieval-augmented visual-language model that learns to use multi-source multi-modal data to answer knowledge-intensive queries, achieves state-of-the-art results on visual question answering and image caption tasks. https://
goo.gle/3qcZwwc -
New ML Methodology for Software Development Assistance Tools
By
–
Today we describe a new methodology for training large #ML models on the historical process of code development to build models that provide software development assistance, like comment resolution, build repair, and tip prediction. See how it’s done at https://t.co/IrReKKjyRx pic.twitter.com/V13NBtEAXY
— Google AI (@GoogleAI) 31 mai 2023Today we describe a new methodology for training large #ML models on the historical process of code development to build models that provide software development assistance, like comment resolution, build repair, and tip prediction. See how it’s done at https://
goo.gle/3oECaPO -
Visual Language Models Enhance Reasoning on Charts and Plots
By
–
Visual language uses pictorial symbols outside of text to convey info & is common in both digital life & the real world. Learn about two models that enhance reasoning on visual language data, such as charts and plots, for state-of-the-art performance → https://
goo.gle/3OHZred -
Barkour: Robotic Agility Benchmark for Quadruped Locomotion
By
–
Presenting Barkour, a robotic agility benchmark that tests the implementation of low-level locomotion skills useful for movement through real-world environments, along with an ML-based example generalist locomotion policy for quadruped robots. Learn more →… pic.twitter.com/DlXQiJx1Ne
— Google AI (@GoogleAI) 26 mai 2023Presenting Barkour, a robotic agility benchmark that tests the implementation of low-level locomotion skills useful for movement through real-world environments, along with an ML-based example generalist locomotion policy for quadruped robots. Learn more →
-
Differentially-Private Algorithm for Hierarchical Graph Clustering
By
–
Introducing a new differentially-private algorithm for clustering hierarchical graphs plus open-source code for a scalable differentially-private k-means algorithm, which can be applied to large datasets using distributed computing. Learn more at:
-
Google Research innovations behind Google I/O 2023 announcements
By
–
Many of the exciting projects and products announced on-stage at #GoogleIO 2023 leveraged innovations by Google Research. Learn about some of the technologies and underlying research behind these exciting announcements at https://
goo.gle/3BXOHAK -
AI Automates Code Review Comments Resolution
By
–
Code-change reviews are a critical and time-consuming part of software development. Learn how we applied recent advances in large sequence models in a real-world setting to automatically resolve code review comments in the day-to-day development workflow →
https://
goo.gle/3MRg8lY -
XTREME-UP Accelerates Research for Under-Represented Languages
By
–
We hope this helps accelerate research that is useful to speakers of under-represented languages & highlight current models’ progress and limitations. Check out some example tasks in XTREME-UP below. (end/3)
-
XTREME-UP: Advancing AI for Under-Represented Languages
By
–
XTREME-UP (Under-Represented and User-Centric with Paucal Data) is distinguished by its (i) use of scarce-data, (ii) user-centric design, and (iii) focus on under-represented languages. (2/3)