This “smart coach” helps LLMs switch between text and code
The CodeSteer system could boost large language models’ accuracy when solving complex problems, such as scheduling shipments in a supply chain.
Can AI really code? Study maps the roadblocks to autonomous software engineering
A team of researchers has mapped the challenges of AI in software development, and outlined a research agenda to move the field forward.
How to more efficiently study complex treatment interactions
A new approach for testing multiple treatment combinations at once could help scientists develop drugs for cancer or genetic disorders.
Simulation-based pipeline tailors training data for dexterous robots
The PhysicsGen system, developed by MIT researchers, helps robots handle items in homes and factories by tailoring training data to a particular machine.
AI shapes autonomous underwater “gliders”
An AI pipeline developed by CSAIL researchers enables unique hydrodynamic designs for bodyboard-sized vehicles that glide underwater and could help scientists gather marine data.
At MIT, musicians make new tools for new tunes
From the classroom to expanding research opportunities, students at MIT Music Technology use design to push the frontier of digital instruments and software for human expression and empowerment.
Study could lead to LLMs that are better at complex reasoning
Researchers developed a way to make large language models more adaptable to challenging tasks like strategic planning or process optimization.
Robotic probe quickly measures key properties of new materials
Developed to analyze new semiconductors, the system could streamline the development of more powerful solar panels.
MIT and Mass General Hospital researchers find disparities in organ acceptance
In an analysis of over 160,000 transplant candidates, researchers found that race is linked to how likely an organ offer is to be accepted on behalf of a patient.
New imaging technique reconstructs the shapes of hidden objects
By leveraging reflections from wireless signals like Wi-Fi, the system could allow robots to find and manipulate items that are blocked from view.
Using generative AI to help robots jump higher and land safely
MIT CSAIL researchers combined GenAI and a physics simulation engine to refine robot designs. The result: a machine that out-jumped a robot designed by humans.
LLMs factor in unrelated information when recommending medical treatments
Researchers find nonclinical information in patient messages — like typos, extra white space, and colorful language — reduces the accuracy of an AI model.
Researchers present bold ideas for AI at MIT Generative AI Impact Consortium kickoff event
Presentations targeted high-impact intersections of AI and other areas, such as health care, business, and education.
Memory safety is at a tipping point
Lincoln Laboratory cybersecurity expert Hamed Okhravi calls for a unified approach to securing computer memory, as a matter of national security.
Unpacking the bias of large language models
In a new study, researchers discover the root cause of a type of bias in LLMs, paving the way for more accurate and reliable AI systems.