Researchers use multiple AI models to collaborate, debate, and improve their reasoning abilities to advance the performance of LLMs while increasing accountability and factual accuracy.
Although computer scientists may initially treat data bias and error as a nuisance, researchers argue it’s a hidden treasure trove for reflecting societal values.
A cross-departmental team is leading efforts to utilize machine learning for increased efficiency in heating and cooling MIT’s buildings.
Jonathan How and his team at the Aerospace Controls Laboratory develop planning algorithms that allow autonomous vehicles to navigate dynamic environments without colliding.
Mens, Manus and Machina (M3S) will design technology, training programs, and institutions for successful human-machine collaboration.
With this new approach, a tailsitter aircraft, ideal for search-and-rescue missions, can plan and execute complex, high-speed acrobatic maneuvers.
The MIT Schwarzman College of Computing awards seed grants to seven interdisciplinary projects exploring AI-augmented management.
MIT researchers investigate the causes of health care disparities among underrepresented groups.
A Lincoln Laboratory team visited Hill Air Force Base in Utah to determine how susceptible the latest-generation mobile network is to detection, geolocation, and jamming.
With a new, user-friendly interface, researchers can quickly design many cellular metamaterial structures that have unique mechanical properties.
“PhotoGuard,” developed by MIT CSAIL researchers, prevents unauthorized image manipulation, safeguarding authenticity in the era of advanced generative models.
A new technique helps a nontechnical user understand why a robot failed, and then fine-tune it with minimal effort to perform a task effectively.
PIGINet leverages machine learning to streamline and enhance household robots' task and motion planning, by assessing and filtering feasible solutions in complex environments.
A new report by MIT researchers highlights the potential of generative AI to help workers with certain writing assignments.
Researchers create a privacy technique that protects sensitive data while maintaining a machine-learning model’s performance.