Natural language boosts LLM performance in coding, planning, and robotics
Three neurosymbolic methods help language models find better abstractions within natural language, then use those representations to execute complex tasks.
Three neurosymbolic methods help language models find better abstractions within natural language, then use those representations to execute complex tasks.
A lauded professor, theoretical physicist, and fusion scientist, Loureiro is keenly positioned to advance the center’s research and education goals.
Senior James Simon wants to effect change in two ways: by quantifying societal issues and working directly with disadvantaged communities.
At MIT’s Festival of Learning 2024, panelists stressed the importance of developing critical thinking skills while leveraging technologies like generative AI.
An expert in robotics and AI, Shah succeeds Steven Barrett at AeroAstro.
The acclaimed cellist and writer discussed his new memoir and reflected on a remarkable musical career.
Fellowship funds graduate studies for outstanding immigrants and children of immigrants.
Lydia Bourouiba’s research on fluid dynamics influenced new guidance from the World Health Organization that will shape how health agencies respond to respiratory infectious diseases.
Programming course for incarcerated people boosts digital literacy and self-efficacy, highlighting potential for reduced recidivism.
The grants fund studies of clean hydrogen production, fetal health-sensing fabric, basalt architecture, and shark-based ocean monitoring.
MIT researchers find circadian variations in liver function play an important role in how drugs are broken down in the body.
The former vice chancellor for undergraduate and graduate education will leverage more than 30 years of experience at the Institute to oversee MIT’s research activities.
The advance offers a way to characterize a fundamental resource needed for quantum computing.
New CLAUDIA system could continuously monitor patients during an infusion and adjust dosage to maintain optimal drug levels.
For the first time, researchers use a combination of MEG and fMRI to map the spatio-temporal human brain dynamics of a visual image being recognized.