To improve robot performance and advance memory capabilities needed for reliable home use, Georgia Tech researchers have developed a new benchmark to evaluate the memory capabilities of vision-language models (VLMs).

Georgia Tech researchers found seven security flaws in CAN XL, a vehicle network standard intended for future driver-assistance systems.

The new AI framework called SlideAgent helps large language models (LLMs) better understand complex visual documents used in the workplace like presentation slide decks, brochures, and reports.

Institute researchers will lead two projects and contribute to several others as part of the Department of Energy’s $5 billion initiative.

Georgia Tech researcher Saman Zonouz is helping shape resilient AI practices for the electricity grid. His work connects workshop planning with research on AI-enabled grid protection and emerging vulnerabilities.

Avant South returns to Tech Square on Oct. 12 – 13 to convene founders, executives, policymakers, investors, researchers, creators, and students to focus on the intersection of technology, culture, and innovation.

A presentation from a fellow GT alumnus led Christian Doetsch to take a more entrepreneurial path in his career.

With more space missions launching each year, finding extraterrestrial life in a microbial form is becoming more plausible. What will the response be back here on Earth if – or when – scientists discover extraterrestrial microbes?

To advance understanding of turbulence, the National Science Foundation is establishing a new, $30 million Science and Technology Center (STC) at Michigan State University. Georgia Tech is among eight universities supporting the center.

The labels refer to whether all of the information about how an AI model works is publicly available and the model can be modified, or whether the model’s developer keeps its inner workings secret and the model itself private property.