MIT tool visualizes and edits “physically impossible” objects
By visualizing Escher-like optical illusions in 2.5 dimensions, the “Meschers” tool could help scientists understand physics-defying shapes and spark new designs.
By visualizing Escher-like optical illusions in 2.5 dimensions, the “Meschers” tool could help scientists understand physics-defying shapes and spark new designs.
Language models follow changing situations using clever arithmetic, instead of sequential tracking. By controlling when these approaches are used, engineers could improve the systems’ capabilities.
Researchers developed an algorithm that lets a robot “think ahead” and consider thousands of potential motion plans simultaneously.
New research using computational vision models suggests the brain’s “ventral stream” might be more versatile than previously thought.
The “PRoC3S” method helps an LLM create a viable action plan by testing each step in a simulation. This strategy could eventually aid in-home robots to complete more ambiguous chore requests.
The MIT sophomore and award-winning memory champion explains what these competitions are all about and why you might want to build a “memory palace.”
By allowing users to clearly see data referenced by a large language model, this tool speeds manual validation to help users spot AI errors.
A new algorithm helps robots practice skills like sweeping and placing objects, potentially helping them improve at important tasks in houses, hospitals, and factories.
New CSAIL research highlights how LLMs excel in familiar scenarios but struggle in novel ones, questioning their true reasoning abilities versus reliance on memorization.
Three neurosymbolic methods help language models find better abstractions within natural language, then use those representations to execute complex tasks.
The MIT Schwarzman College of Computing building will form a new cluster of connectivity across a spectrum of disciplines in computing and artificial intelligence.
Researchers coaxed a family of generative AI models to work together to solve multistep robot manipulation problems.
Training artificial neural networks with data from real brains can make computer vision more robust.
A new tool brings the benefits of AI programming to a much broader class of problems.
MIT researchers are discovering which parts of the brain are engaged when a person evaluates a computer program.