Deep-learning system explores materials’ interiors from the outside
A new method could provide detailed information about internal structures, voids, and cracks, based solely on data about exterior conditions.
Search Stories
MIT engineers “grow” atomically thin transistors on top of computer chips
A new low-temperature growth and fabrication technology allows the integration of 2D materials directly onto a silicon circuit, which could lead to denser and more powerful chips.
Making property assessments as simple as snapping a picture
The technology of MIT alumni-founded Hosta a.i. creates detailed property assessments from photos.
AI system can generate novel proteins that meet structural design targets
These tunable proteins could be used to create new materials with specific mechanical properties, like toughness or flexibility.
Drones navigate unseen environments with liquid neural networks
MIT researchers exhibit a new advancement in autonomous drone navigation, using brain-inspired liquid neural networks that excel in out-of-distribution scenarios.
MIT CSAIL researchers discuss frontiers of generative AI
Experts convene to peek under the hood of AI-generated code, language, and images as well as its capabilities, limitations, and future impact.
Understanding our place in the universe
Martin Luther King Jr. Scholar Brian Nord trains machines to explore the cosmos and fights for equity in research.
3 Questions: Yossi Sheffi on AI and the future of the supply chain
In a new book, the founder of MIT’s Center for Transportation and Logistics examines how increasingly automated industries can sustain jobs.
Jacob Andreas and Mingda Li honored with Junior Bose Award for Excellence in Teaching
Award is given each year by the School of Engineering to an outstanding educator up for promotion to associate professor without tenure.
A four-legged robotic system for playing soccer on various terrains
“DribbleBot” can maneuver a soccer ball on landscapes such as sand, gravel, mud, and snow, using reinforcement learning to adapt to varying ball dynamics.
Speeding up drug discovery with diffusion generative models
MIT researchers built DiffDock, a model that may one day be able to find new drugs faster than traditional methods and reduce the potential for adverse side effects.
A method for designing neural networks optimally suited for certain tasks
With the right building blocks, machine-learning models can more accurately perform tasks like fraud detection or spam filtering.
School of Engineering welcomes new faculty
Eleven new faculty members join six of the school's academic departments and institutes.
Bob Metcalfe ’69 wins $1 million Turing Award
CSAIL research affiliate and MIT Corporation life member emeritus is honored with the “Nobel Prize of computing” for Ethernet invention.
Learning to grow machine-learning models
New LiGO technique accelerates training of large machine-learning models, reducing the monetary and environmental cost of developing AI applications.