Newsroom
language models
-

How to Generate and Verify LLM-Generated Lean Proofs for Your Mathematical Needs
A hands-on workshop on using large language models and Lean to formalize mathematical claims, audit generated proofs, and determine whether a machine-verified result actually says what you intended. When Lean says a proof is correct, what exactly has been proved? Large language models can translate mathematical arguments into Lean, but a proof that compiles is…
-
S&DS Seminar: Yuting Wei (Pennsylvania), “Transformers Meet In-Context Learning: A Universal Approximation Theory
Abstract: Modern large language models are capable of in-context learning, the ability to perform new tasks at inference time using only a handful of input-output examples in the prompt, without any fine-tuning or parameter updates. We develop a universal approximation theory to better understand how transformers enable in-context learning. For any class of functions (each…
-
FDS Colloquium: Kristina Gligoric (Stanford), “Supporting policies and interventions to promote healthy and sustainable habits”
Abstract: Data science tools create new opportunities to assist policy-makers. For example, enabling healthy and sustainable diets is key to addressing preventable diseases and climate change. How can data science methods help policy-makers in developing interventions that address these and other societal challenges? I develop causal inference tools for explaining decision-making and LLM methods for…
-
-
FDS Colloquium: Song Mei (Berkeley), “Revisiting neural network approximation theory in the age of generative AI”
Optional Zoom link: https://yale.zoom.us/j/97222935172 Abstract: Textbooks on deep learning theory primarily perceive neural networks as universal function approximators. While this classical viewpoint is fundamental, it inadequately explains the impressive capabilities of modern generative AI models such as language models and diffusion models. This talk puts forth a refined perspective: neural networks often serve as algorithm approximators,…
