Enabling small language models to solve complex reasoning tasks
The “self-steering” DisCIPL system directs small models to work together on tasks with constraints, like itinerary planning and budgeting.
The “self-steering” DisCIPL system directs small models to work together on tasks with constraints, like itinerary planning and budgeting.
The technique can help scientists in economics, public health, and other fields understand whether to trust the results of their experiments.
With insect-like speed and agility, the tiny robot could someday aid in search-and-rescue missions.
Large language models can learn to mistakenly link certain sentence patterns with specific topics — and may then repeat these patterns instead of reasoning.
A new approach developed at MIT could help a search-and-rescue robot navigate an unpredictable environment by rapidly generating an accurate map of its surroundings.
MIT PhD student and CSAIL researcher Justin Kay describes his work combining AI and computer vision systems to monitor the ecosystems that support our planet.
Economics doctoral student Whitney Zhang investigates how technologies and organizational decisions shape labor markets.
With SCIGEN, researchers can steer AI models to create materials with exotic properties for applications like quantum computing.
System developed at MIT could provide realistic predictions for a wide variety of reactions, while maintaining real-world physical constraints.
By visualizing Escher-like optical illusions in 2.5 dimensions, the “Meschers” tool could help scientists understand physics-defying shapes and spark new designs.