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.
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.
The MIT senior will pursue postgraduate studies in computer science in Ireland.
Engineers working on “analog deep learning” have found a way to propel protons through solids at unprecedented speeds.
A new computational model could explain differences in recognizing facial emotions.
Martin Luther King Jr. Scholar bridges disciplines to translate vision into elegant math and neuroscience theory.
Professor Bilge Yildiz finds patterns in the behavior of ions across applications.