Computer vision system marries image recognition and generation
MAGE merges the two key tasks of image generation and recognition, typically trained separately, into a single system.
Download RSS feed: News Articles / In the Media / Audio
MAGE merges the two key tasks of image generation and recognition, typically trained separately, into a single system.
The system analyzes the likelihood that an attacker could thwart a certain security scheme to steal secret information.
Six teams conducting research in AI, data science, and machine learning receive funding for projects that have potential commercial applications.
MIT researchers characterize gene expression patterns for 22,500 brain vascular cells across 428 donors, revealing insights for Alzheimer’s onset and potential treatments.
The inaugural SERC Symposium convened experts from multiple disciplines to explore the challenges and opportunities that arise with the broad applicability of computing in many aspects of society.
By applying a language model to protein-drug interactions, researchers can quickly screen large libraries of potential drug compounds.
The scientists used a natural language-based logical inference dataset to create smaller language models that outperformed much larger counterparts.
A new multimodal technique blends major self-supervised learning methods to learn more similarly to humans.
Using insights into how people intuit others’ emotions, researchers have designed a model that approximates this aspect of human social intelligence.
Selecting the right method gives users a more accurate picture of how their model is behaving, so they are better equipped to correctly interpret its predictions.
Researchers develop an algorithm that decides when a “student” machine should follow its teacher, and when it should learn on its own.
Violence Prevention and Response and the Institute Discrimination and Harassment Response Office celebrate students and employees for their efforts in combating sexual misconduct.
Researchers create a new simulation tool for robots to manipulate complex fluids in a step toward helping them more effortlessly assist with daily tasks.
By mapping the volumes of objects, rather than their surfaces, a new technique could yield solutions to computer graphics problems in animation and CAD.
This machine-learning method could assist with robotic scene understanding, image editing, or online recommendation systems.