Enhancing LLM collaboration for smarter, more efficient solutions
“Co-LLM” algorithm helps a general-purpose AI model collaborate with an expert large language model by combining the best parts of both answers, leading to more factual responses.
Startup’s displays engineer light to generate immersive experiences without the headsets
“We are adding a new layer of control between the world of computers and what your eyes see,” says Barmak Heshmat, co-founder of Brelyon and a former MIT postdoc.
A fast and flexible approach to help doctors annotate medical scans
“ScribblePrompt” is an interactive AI framework that can efficiently highlight anatomical structures across different medical scans, assisting medical workers to delineate regions of interest and abnormalities.
Sam Madden named faculty head of computer science in EECS
Computer scientist who specializes in database management systems joins the leadership of the Department of Electrical Engineering and Computer Science.
For developing designers, there’s magic in 2.737 (Mechatronics)
Mechatronics combines electrical and mechanical engineering, but above all else it’s about design.
Study: Transparency is often lacking in datasets used to train large language models
Researchers developed an easy-to-use tool that enables an AI practitioner to find data that suits the purpose of their model, which could improve accuracy and reduce bias.
How MIT’s online resources provide a “highly motivating, even transformative experience”
Charalampos Sampalis explores all that MIT Open Learning has to offer while growing his career in Athens, Greece.
A framework for solving parabolic partial differential equations
A new algorithm solves complicated partial differential equations by breaking them down into simpler problems, potentially guiding computer graphics and geometry processing.
Toward a code-breaking quantum computer
Building on a landmark algorithm, researchers propose a way to make a smaller and more noise-tolerant quantum factoring circuit for cryptography.
AI assistant monitors teamwork to promote effective collaboration
An AI team coordinator aligns agents’ beliefs about how to achieve a task, intervening when necessary to potentially help with tasks in search and rescue, hospitals, and video games.
LLMs develop their own understanding of reality as their language abilities improve
In controlled experiments, MIT CSAIL researchers discover simulations of reality developing deep within LLMs, indicating an understanding of language beyond simple mimicry.
MIT researchers use large language models to flag problems in complex systems
The approach can detect anomalies in data recorded over time, without the need for any training.
Helping robots practice skills independently to adapt to unfamiliar environments
A new algorithm helps robots practice skills like sweeping and placing objects, potentially helping them improve at important tasks in houses, hospitals, and factories.
New transistor’s superlative properties could have broad electronics applications
Ultrathin material whose properties “already meet or exceed industry standards” enables superfast switching, extreme durability.
Study: When allocating scarce resources with AI, randomization can improve fairness
Introducing structured randomization into decisions based on machine-learning model predictions can address inherent uncertainties while maintaining efficiency.