New research reveals a scalable technique that uses synthetic data to improve the accuracy of AI models that recognize images.
A new technique identifies and removes the training examples that contribute most to a machine-learning model’s failures.
With models like AlphaFold3 limited to academic research, the team built an equivalent alternative, to encourage innovation more broadly.
New CSAIL research highlights how LLMs excel in familiar scenarios but struggle in novel ones, questioning their true reasoning abilities versus reliance on memorization.
More accurate uncertainty estimates could help users decide about how and when to use machine-learning models in the real world.
Researchers have made strides toward machine-learning models that can help doctors more efficiently find information in a patient’s health record.
This machine-learning system can simulate how a listener would hear a sound from any point in a room.
CSAIL researchers introduce a novel approach allowing robots to be trained in simulations of scanned home environments, paving the way for customized household automation accessible to anyone.
New dataset of “illusory” faces reveals differences between human and algorithmic face detection, links to animal face recognition, and a formula predicting where people most often perceive faces.
A new method can train a neural network to sort corrupted data while anticipating next steps. It can make flexible plans for robots, generate high-quality video, and help AI agents navigate digital environments.