Study could lead to LLMs that are better at complex reasoning

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

Adam Zewe | MIT News • mit
yesterday ~6 min

Inroads to personalized AI trip planning

A new framework from the MIT-IBM Watson AI Lab supercharges language models, so they can reason over, interactively develop, and verify valid, complex travel agendas.

Lauren Hinkel | MIT-IBM Watson AI Lab • mit
June 10, 2025 ~9 min


AI-enabled control system helps autonomous drones stay on target in uncertain environments

The system automatically learns to adapt to unknown disturbances such as gusting winds.

Adam Zewe | MIT News • mit
June 9, 2025 ~8 min

Overlooked cells might explain the human brain’s huge storage capacity

MIT researchers developed a new model of memory that includes critical contributions from astrocytes, a class of brain cells.

Anne Trafton | MIT News • mit
May 27, 2025 ~9 min

AI learns how vision and sound are connected, without human intervention

This new machine-learning model can match corresponding audio and visual data, which could someday help robots interact in the real world.

Adam Zewe | MIT News • mit
May 22, 2025 ~7 min

A visual pathway in the brain may do more than recognize objects

New research using computational vision models suggests the brain’s “ventral stream” might be more versatile than previously thought.

Anne Trafton | MIT News • mit
April 15, 2025 ~9 min

Training LLMs to self-detoxify their language

A new method from the MIT-IBM Watson AI Lab helps large language models to steer their own responses toward safer, more ethical, value-aligned outputs.

Lauren Hinkel | MIT-IBM Watson AI Lab • mit
April 14, 2025 ~11 min

Could LLMs help design our next medicines and materials?

A new method lets users ask, in plain language, for a new molecule with certain properties, and receive a detailed description of how to synthesize it.

Adam Zewe | MIT News • mit
April 9, 2025 ~8 min


New method assesses and improves the reliability of radiologists’ diagnostic reports

The framework helps clinicians choose phrases that more accurately reflect the likelihood that certain conditions are present in X-rays.

Adam Zewe | MIT News • mit
April 4, 2025 ~8 min

Researchers teach LLMs to solve complex planning challenges

This new framework leverages a model’s reasoning abilities to create a “smart assistant” that finds the optimal solution to multistep problems.

Adam Zewe | MIT News • mit
April 2, 2025 ~7 min

/

9