Enhancing LLM collaboration for smarter, more efficient solutions
“Co-LLM” algorithm helps a general-purpose AI model collaborate with an expert large language model by combining the best parts of both answers, leading to more factual responses.
Computer science and technology
A fast and flexible approach to help doctors annotate medical scans
“ScribblePrompt” is an interactive AI framework that can efficiently highlight anatomical structures across different medical scans, assisting medical workers to delineate regions of interest and abnormalities.
Study: Transparency is often lacking in datasets used to train large language models
Researchers developed an easy-to-use tool that enables an AI practitioner to find data that suits the purpose of their model, which could improve accuracy and reduce bias.
A framework for solving parabolic partial differential equations
A new algorithm solves complicated partial differential equations by breaking them down into simpler problems, potentially guiding computer graphics and geometry processing.
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.
MIT researchers use large language models to flag problems in complex systems
The approach can detect anomalies in data recorded over time, without the need for any training.
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.
Helping Olympic athletes optimize their performance, one stride at a time
The startup Striv, which went through MIT’s START.nano accelerator program, has developed a shoe sole for athletes that can track force, movement, and form.
Study: When allocating scarce resources with AI, randomization can improve fairness
Introducing structured randomization into decisions based on machine-learning model predictions can address inherent uncertainties while maintaining efficiency.
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.