Language models follow changing situations using clever arithmetic, instead of sequential tracking. By controlling when these approaches are used, engineers could improve the systems’ capabilities.
The CodeSteer system could boost large language models’ accuracy when solving complex problems, such as scheduling shipments in a supply chain.
A team of researchers has mapped the challenges of AI in software development, and outlined a research agenda to move the field forward.
A new approach for testing multiple treatment combinations at once could help scientists develop drugs for cancer or genetic disorders.
Researchers developed a way to make large language models more adaptable to challenging tasks like strategic planning or process optimization.
Developed to analyze new semiconductors, the system could streamline the development of more powerful solar panels.
In a new study, researchers discover the root cause of a type of bias in LLMs, paving the way for more accurate and reliable AI systems.
The MIT Ethics of Computing Research Symposium showcases projects at the intersection of technology, ethics, and social responsibility.
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.
The system automatically learns to adapt to unknown disturbances such as gusting winds.
