Seminar @ Cornell Tech: Avi Schwarzschild

Bloomberg Center Room 401 / Cornell Tech Campus / NYC

Even with the widespread and increasing use of AI, the safety implications and the reasoning capabilities should be better understood. In Avi Schwarzschild's talk entitled, "Safe and Reasonable AI," he will first discuss memorization in LLMs through the lens of copyright infringement. Then, Schwarzschild will discuss recent research on reasoning in neural networks.