A Georgia Tech Ph.D. student is investigating whether internal signals in large language models could help identify harmful behavior before it reaches users.

Georgia Tech researchers have developed a new neural framework that examines how different training sources influence empathy and social reasoning within large language models.

Georgia Tech researchers found that instruction changes can reduce chatbots’ reinforcement of delusional beliefs.

Maritime cybersecurity training leaves sailors vulnerable to attacks that manipulate ship systems without obvious failures. The Georgia Tech study identifies weaknesses in preparation and threat recognition among military mariners.

Researchers find that deleted local AI chats may remain recoverable from a phone’s memory through a new tool called ORISA.

The three-year initiative gives researchers greater access to AI tools, training, and computing power to help accelerate scientific breakthroughs.

AI agents don’t go rogue. That’s something only humans do.

The three-year initiative gives researchers greater access to AI tools, training, and computing power to help accelerate scientific breakthroughs.

The collaboration will support research in robotics, industrial and systems engineering, and aerospace technology while fostering innovation in foundational and emerging technologies. 

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).