A lock-and-key with language model in the background.

New Method Efficiently Safeguards Sensitive AI Training Data

Adam Zewe | MIT News

The approach maintains an AI model’s accuracy while ensuring attackers can’t extract secret information.

abstract visualization of integrated circuit and system co-design with layered blue and grey square circuits

Can We Rely on Future AI ICs?- Robustness Design as Key Challenge for System Technology Co-Optimization

Thursday, November 21, 2024 | 1:00 - 2:00pm ET
Virtual

Speaker: Harald Gossner, Intel

Generative AI for Microsystem Design: Possibility and Opportunity

Wednesday, May 22, 2024 | 12:00 - 1:00pm ET
Hybrid

Zoom & Grier Room A (34-401A)
50 Vassar Street Cambridge, MA

Jonathan Ragan-Kelley stands outdoors in Budapest, with the city as a backdrop

Creating Bespoke Programming Languages for Efficient Visual AI Systems

Lauren Hinkel | MIT-IBM Watson AI Lab

Associate Professor Jonathan Ragan-Kelley optimizes how computer graphics and images are processed for the hardware of today and tomorrow.

abstract representation of futuristic memory computing data architecture systems

Prospects of Future In- and Near-Memory Computing Systems

Wednesday, March 20, 2024 | 12:00 - 1:00pm ET
Hybrid

Zoom & Allen Room (36-462)
50 Vassar Street Cambridge, MA

Illustration shows a Venn diagram of three overlapping circles, each with a colorful qubit represented as a circle with an arrow through it. Colorful lines connect the three. Other qubits fly around.

Technique Could Improve the Sensitivity of Quantum Sensing Devices

Adam Zewe | MIT News

New method lets researchers identify and control larger numbers of atomic-scale defects, to build a bigger system of qubits.

A cell phone peeks out from the pocket of a person wearing jeans, a belt, and a plaid shirt. In the background and on the cell phone’s screen are stylized connected nodes representing a neural network.

Technique Enables AI on Edge Devices to Keep Learning Over Time

Adam Zewe | MIT News

With the PockEngine training method, machine-learning models can efficiently and continuously learn from user data on edge devices like smartphones.

MIT Engineers are on a Failure-Finding Mission

Jennifer Chu | MIT News

The team’s new algorithm finds failures and fixes in all sorts of autonomous systems, from drone teams to power grids.