Researchers combine statistical and symbolic artificial intelligence techniques to speed learning and improve transparency.
By enabling models to see the world more like humans do, the work could help improve driver safety and shed light on human behavior.
Associate Professor Jonathan Ragan-Kelley optimizes how computer graphics and images are processed for the hardware of today and tomorrow.
Artificial intelligence (AI) can become more efficient and reliable if it is made to mimic biological models. New approaches in AI research are hugely successful in experiments.
On Friday, June 11, 2021, the Department of the Air Force (DAF)-MIT Artificial Intelligence Accelerator (AIA) announced the AIA 2020 Awards for significant contributions and excellence. The recipients were selected from over 150 Airmen, MIT Lincoln Laboratory personnel, and MIT staff and students involved in this partnership.
researchers describe an AI system — Foley Music — that can generate “plausible” music from silent videos of musicians playing instruments. They say it works on a variety of music performances and outperforms “several” existing systems in generating music that’s pleasant to listen to.
MIT CSAIL paper measures how quickly the algorithms behind language models like GPT-4 have improved over time.
Can you recognize a digitally manipulated video when you see one? It’s harder than most people realize. As the technology to produce realistic “deepfakes” becomes more easily available, distinguishing fact from fiction will only get more challenging.
MIT CSAIL postdoc Nauman Dawalatabad explores ethical considerations, challenges in spear-phishing defense, and the optimistic future of AI-created voices across various sectors.
Researchers have created a unifying framework that can help scientists combine existing ideas to improve AI models or create new ones.