Get the latest tech news

IBM's Dmitry Krotov wants to crack the 'physics' of memory

Dima Krotov is searching for an AI architecture that is both interpretable and could explain how our own memory works.

“You can see where patterns in the energy transformer are stored, and you can watch as the model gradually extracts the relevant information from its memory banks,” says Benjamin Hoover, an IBM researcher who works closely with Krotov. “These spurious states are very stable and reproducible, but they are also different from the training data,” said Bao Pham, an IBM intern and PhD student at RPI who recently presented the work at ICLR 2025 ’s associative memory workshop. “For years, people thought astrocytes were just support cells, but now, thanks to better imaging tools, we’re starting to realize they play a much bigger role,” said Leo Kozachkov, who worked on the project as a PhD student at MIT and is now a Goldstine postdoctoral fellow at IBM.

Get the Android app