Rax: Composable Learning-to-Rank Using JAX

Favorite Posted by Rolf Jagerman and Honglei Zhuang, Software Engineers, Google Research Ranking is a core problem across a variety of domains, such as search engines, recommendation systems, or question answering. As such, researchers often utilize learning-to-rank (LTR), a set of supervised machine learning techniques that optimize for the utility

Read More
Shared by Google AI Technology August 11, 2022

Efficient Video-Text Learning with Iterative Co-tokenization

Favorite Posted by AJ Piergiovanni and Anelia Angelova, Research Scientists, Google Research, Brain Team Video is an ubiquitous source of media content that touches on many aspects of people’s day-to-day lives. Increasingly, real-world video applications, such as video captioning, video content analysis, and video question-answering (VideoQA), rely on models that

Read More
Shared by Google AI Technology August 9, 2022

Introducing the Google Universal Image Embedding Challenge

Favorite Posted by Bingyi Cao, Software Engineer, Google Research, and Mário Lipovský, Software Engineer, Google Lens Computer vision models see daily application for a wide variety of tasks, ranging from object recognition to image-based 3D object reconstruction. One challenging type of computer vision problem is instance-level recognition (ILR) — given

Read More
Shared by Google AI Technology August 4, 2022

Building Efficient Multiple Visual Domain Models with Multi-path Neural Architecture Search

Favorite Posted by Qifei Wang, Senior Software Engineer, and Feng Yang, Senior Staff Software Engineer, Google Research Deep learning models for visual tasks (e.g., image classification) are usually trained end-to-end with data from a single visual domain (e.g., natural images or computer generated images). Typically, an application that completes visual

Read More
Shared by Google AI Technology August 3, 2022

Efficient Sequence Modeling for On-Device ML

Favorite Posted by Arun Kandoor, Software Engineer, Google Research The increasing demand for machine learning (ML) model inference on-device (for mobile devices, tablets, etc.) is driven by the rise of compute-intensive applications, the need to keep certain data on device for privacy and security reasons, and the desire to provide

Read More
Shared by Google AI Technology August 3, 2022

Enhancing Backpropagation via Local Loss Optimization

Favorite Posted by Ehsan Amid, Research Scientist, and Rohan Anil, Principal Engineer, Google Research, Brain Team While model design and training data are key ingredients in a deep neural network’s (DNN’s) success, less-often discussed is the specific optimization method used for updating the model parameters (weights). Training DNNs involves minimizing

Read More
Shared by Google AI Technology July 29, 2022

Look and Talk: Natural Conversations with Google Assistant

Favorite Posted by Tuan Anh Nguyen, Staff Software Engineer, Google Assistant, and Sourish Chaudhuri, Staff Software Engineer, Google Research In natural conversations, we don’t say people’s names every time we speak to each other. Instead, we rely on contextual signaling mechanisms to initiate conversations, and eye contact is often all

Read More
Shared by Google AI Technology July 27, 2022

ML-Enhanced Code Completion Improves Developer Productivity

Favorite Posted by Maxim Tabachnyk, Staff Software Engineer and Stoyan Nikolov, Senior Engineering Manager, Google Research The increasing complexity of code poses a key challenge to productivity in software engineering. Code completion has been an essential tool that has helped mitigate this complexity in integrated development environments (IDEs). Conventionally, code

Read More
Shared by Google AI Technology July 26, 2022

Training Generalist Agents with Multi-Game Decision Transformers

Favorite Posted by Winnie Xu, Student Researcher and Kuang-Huei Lee, Software Engineer, Google Research, Brain Team Current deep reinforcement learning (RL) methods can train specialist artificial agents that excel at decision-making on various individual tasks in specific environments, such as Go or StarCraft. However, little progress has been made to

Read More
Shared by Google AI Technology July 21, 2022