MIT

Q&A: Enabling more human-like interactions and understanding in multimodal foundation models

mit-ibm-multimodal

Senior Research Scientist Jim Glass discusses how his MIT-IBM Computing Research Lab collaboration connects perception and language, and addresses the shortcoming of current models. Lauren Hinkel | MIT-IBM Computing Research Lab Publication Date: November 20, 2026 Press Inquiries Press Contact: Lauren Hinkel Email: hinkell@mit.edu MIT-IBM Watson AI Lab Close Caption: The MIT-IBM Computing Research Lab of Jim Glass connects text, imagery, video, and audio in foundation models. Credits: Image: AdobeStock Humans experience and interact with the world through sensory information. This could mean learning correspondences between the sound of bird chirps and the word “robin,” or being able to visually…

Continue reading at MIT news.mit.edu
Advertisement