Researchers proposed a way for robots to find objects in households where things get moved around. Andrey Kurenkov and colleagues at Stanford University introduced Node Edge Predictor, a model that learned to predict where objects were located in houses.
In a study, models used to detect people walking on streets and sidewalks performed less well on adults with darker skin and children of all skin tones.
In a study, models used to detect people walking on streets and sidewalks performed less well on adults with darker skin and children of all skin tones.
A pretrained large language model has helped a robot resolve high-level commands into sequences of subtasks. It can do this more precisely with additional training — both on language-vision tasks and robotics tasks.
A pretrained large language model has helped a robot resolve high-level commands into sequences of subtasks. It can do this more precisely with additional training — both on language-vision tasks and robotics tasks.
The transformer architecture is astonishingly powerful but notoriously slow. Researchers have developed numerous tweaks to accelerate it — enough to warrant a look at how these alternatives work, their strengths, and their weaknesses.
The transformer architecture is astonishingly powerful but notoriously slow. Researchers have developed numerous tweaks to accelerate it — enough to warrant a look at how these alternatives work, their strengths, and their weaknesses.
Online sorting algorithms run trillions of times a day to organize lists according to users’ interests. New work found faster alternatives. Daniel J. Mankowitz and colleagues at Google developed AlphaDev, a system that learned to generate algorithms that sort three...
Online sorting algorithms run trillions of times a day to organize lists according to users’ interests. New work found faster alternatives. Daniel J. Mankowitz and colleagues at Google developed AlphaDev, a system that learned to generate algorithms that sort three...
Generated images can be more effective than real ones in training a vision model to classify images. Yonglong Tian, Lijie Fan, and colleagues at Google and MIT introduced StableRep, a self-supervised method that trains vision transformers on images generated by...
Generated images can be more effective than real ones in training a vision model to classify images. Yonglong Tian, Lijie Fan, and colleagues at Google and MIT introduced StableRep, a self-supervised method that trains vision transformers on images generated by...
Large language models may help psychiatrists resolve unanswered questions about mental illness. Researchers from University College London, Beijing Normal University, and Lisbon’s Champalimaud Centre for the Unknown used a large language model to...
Large language models may help psychiatrists resolve unanswered questions about mental illness. Researchers from University College London, Beijing Normal University, and Lisbon’s Champalimaud Centre for the Unknown used a large language model to...
Text-to-image generators often miss details in text prompts, and sometimes they misunderstand parts of a prompt entirely. Synthetic captions can help them follow prompts more closely.
Text-to-image generators often miss details in text prompts, and sometimes they misunderstand parts of a prompt entirely. Synthetic captions can help them follow prompts more closely.
Stay updated with weekly AI News and Insights delivered to your inbox