Keynote 2: Understanding How Knowledge Can Be Localized, Unlearned, or Verified in Foundation Models

Dr. Feizi is the Founder and CEO of RELAI (relai.ai), a startup focused on advancing AI reliability. He is also an Associate Professor (on leave) in the Computer Science Department at the University of Maryland, College Park. Dr. Feizi earned his Ph.D. from MIT and conducted postdoctoral research at Stanford University. He received the 2024 Presidential Early Career Award for Scientists and Engineers (PECASE)—the highest honor granted by the U.S. government to early-career researchers. His distinctions also include the ONR Young Investigator Award, NSF CAREER Award, ARO Early Career Program Award, two best paper awards, the Ernst Guillemin Thesis Award, a teaching award, and over twenty research awards from federal agencies and industry partners. His work has been featured in major media outlets including The New York Times, The Washington Post, BBC, MIT Technology Review, Bloomberg, and The Wire. In 2024, he testified before the U.S. House Bipartisan Task Force on AI, underscoring his commitment to ensuring the safety and reliability of AI technologies.