3 Questions: How to prove humanity online
AI agents could soon become indistinguishable from humans online. Could “personhood credentials” protect people against digital imposters?
Computer Science and Artificial Intelligence Laboratory (CSAIL)
LLMs develop their own understanding of reality as their language abilities improve
In controlled experiments, MIT CSAIL researchers discover simulations of reality developing deep within LLMs, indicating an understanding of language beyond simple mimicry.
Helping robots practice skills independently to adapt to unfamiliar environments
New algorithm helps robots practice skills like sweeping and placing objects, potentially helping them improve at important tasks in houses, hospitals, and factories.
Precision home robots learn with real-to-sim-to-real
CSAIL researchers introduce a novel approach allowing robots to be trained in simulations of scanned home environments, paving the way for customized household automation accessible to anyone.
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.
Creating and verifying stable AI-controlled systems in a rigorous and flexible way
Neural network controllers provide complex robots with stability guarantees, paving the way for the safer deployment of autonomous vehicles and industrial machines.
AI method radically speeds predictions of materials’ thermal properties
The approach could help engineers design more efficient energy-conversion systems and faster microelectronic devices, reducing waste heat.
Reasoning skills of large language models are often overestimated
New CSAIL research highlights how LLMs excel in familiar scenarios but struggle in novel ones, questioning their true reasoning abilities versus reliance on memorization.
MIT researchers introduce generative AI for databases
This new tool offers an easier way for people to analyze complex tabular data.
Understanding the visual knowledge of language models
LLMs trained primarily on text can generate complex visual concepts through code with self-correction. Researchers used these illustrations to train an image-free computer vision system to recognize real photos.