MIT researchers advance automated interpretability in AI models
MAIA is a multimodal agent that can iteratively design experiments to better understand various components of AI systems.
Learn about artificial intelligence, GPT usage, prompt engineering and other technology news and updates from Land of GPT. The site aggregates articles from official RSS feeds under their original authorship. Each article has a do-follow link to the original source.
MAIA is a multimodal agent that can iteratively design experiments to better understand various components of AI systems.
New CSAIL research highlights how LLMs excel in familiar scenarios but struggle in novel ones, questioning their true reasoning abilities versus reliance on memorization.
The SPARROW algorithm automatically identifies the best molecules to test as potential new medicines, given the vast number of factors affecting each choice.
With generative AI models, researchers combined robotics data from different sources to help robots learn better.
Three neurosymbolic methods help language models find better abstractions within natural language, then use those representations to execute complex tasks.
Researchers have developed a security solution for power-hungry AI models that offers protection against two common attacks.
A new technique can be used to predict the actions of human or AI agents who behave suboptimally while working toward unknown goals.
MIT researchers plan to search for proteins that could be used to measure electrical activity in the brain.
FeatUp, developed by MIT CSAIL researchers, boosts the resolution of any deep network or visual foundation for computer vision systems.
MIT engineers developed a tag that can reveal with near-perfect accuracy whether an item is real or fake. The key is in the glue on the back of the tag.