Unraveling Adversarial Problems
David delves into the persistent challenge of adversarial examples in computer vision, highlighting the susceptibility of vision transformers. Despite progress, the mystery remains unsolved, leaving threads to explore for potential exponential improvements. Daniel contrasts the confined nature of large language models (LLMs) within linguistic rules with the broader world connections, hinting at the complexity beyond language boundaries.In this clip
From this podcast
The Gradient
David Pfau: Manifold Factorization and AI for Science
Related Questions