Yoon Kim

MIT-IBM Watson AI Lab researchers developed an expressive architecture that provides better state tracking and sequential reasoning in LLMs over long texts.

With a new method developed at MIT, an LLM behaves more like a student, writing notes that it studies to memorize new information.

MIT PhD students who interned with the MIT-IBM Watson AI Lab Summer Program are pushing AI tools to be more flexible, efficient, and grounded in truth.

Researchers developed a way to make large language models more adaptable to challenging tasks like strategic planning or process optimization.

Words like “no” and “not” can cause this popular class of AI models to fail unexpectedly in high-stakes settings, such as medical diagnosis.