Making AI-generated code more accurate in any language
A new technique automatically guides an LLM toward outputs that adhere to the rules of whatever programming language or other format is being used.
A new technique automatically guides an LLM toward outputs that adhere to the rules of whatever programming language or other format is being used.
A new method from the MIT-IBM Watson AI Lab helps large language models to steer their own responses toward safer, more ethical, value-aligned outputs.
The approach maintains an AI model’s accuracy while ensuring attackers can’t extract secret information.
A new method lets users ask, in plain language, for a new molecule with certain properties, and receive a detailed description of how to synthesize it.
“InteRecon” enables users to capture items in a mobile app and reconstruct their interactive features in mixed reality. The tool could assist in education, medical environments, museums, and more.
The framework helps clinicians choose phrases that more accurately reflect the likelihood that certain conditions are present in X-rays.
Ana Trišović, who studies the democratization of AI, reflects on a career path that she began as a student downloading free MIT resources in Serbia.
The American Association for the Advancement of Science recognizes six current affiliates and 27 additional MIT alumni for their efforts to advance science and related fields.
The Tactile Vega-Lite system, developed at MIT CSAIL, streamlines the tactile chart design process; could help educators efficiently create these graphics and aid designers in making precise changes.
Stuart Levine ’97, director of MIT’s BioMicro Center, keeps departmental researchers at the forefront of systems biology.
“Xstrings” method enables users to produce cable-driven objects, automatically assembling bionic robots, sculptures, and dynamic fashion designs.
The Exo 2 programming language enables reusable scheduling libraries external to compilers.
New research could allow a person to correct a robot’s actions in real-time, using the kind of feedback they’d give another human.
A first history of the document security technology, co-authored by MIT Libraries’ Jana Dambrogio, provides new tools for interdisciplinary research.
Annual award honors early-career researchers for creativity, innovation, and research accomplishments.