Teaching AI agents to ask better questions by playing “Battleship”
MIT researchers use the classic game as a test bed for AI agents, finding a small AI model can outperform the biggest ones at 1 percent of the cost.
MIT researchers use the classic game as a test bed for AI agents, finding a small AI model can outperform the biggest ones at 1 percent of the cost.
To help generative AI models create durable, real-world accessories and decor, the PhysiOpt system runs physics simulations and makes subtle tweaks to its 3D blueprints.
EnCompass executes AI agent programs by backtracking and making multiple attempts, finding the best set of outputs generated by an LLM. It could help coders work with AI agents more efficiently.
“MechStyle” allows users to personalize 3D models, while ensuring they’re physically viable after fabrication, producing unique personal items and assistive technology.
The “self-steering” DisCIPL system directs small models to work together on tasks with constraints, like itinerary planning and budgeting.
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.
To reduce waste, the Refashion program helps users create outlines for adaptable clothing, such as pants that can be reconfigured into a dress. Each component of these pieces can be replaced, rearranged, or restyled.
New tool from MIT CSAIL creates realistic virtual kitchens and living rooms where simulated robots can interact with models of real-world objects, scaling up training data for robot foundation models.
MIT CSAIL researchers developed a tool that can model the shape and movements of fetuses in 3D, potentially assisting doctors in finding abnormalities and making diagnoses.
By visualizing Escher-like optical illusions in 2.5 dimensions, the “Meschers” tool could help scientists understand physics-defying shapes and spark new designs.