Newsroom
Natural Language Processing
-
Dissertation Defense: Anay Mehrotra, “Learning Theory in the Wild: Foundations of Missing Data and Language Generation”
Abstract: What can be learned from data? This fundamental question in machine learning takes on new complexity in modern pipelines where classical assumptions fail—both in how data is generated and in how learning objectives are defined. This thesis develops foundations for learning under these complex conditions, revealing how violations of traditional assumptions transform not just…
-
FDS Colloquium: Tom McCoy (Yale), “Understanding AI systems by understanding their training data: Memorization, generalization, and points in between”
Abstract: Large language models (LLMs) can perform a wide range of tasks impressively well. To what extent are these abilities driven by shallow heuristics vs. deeper abstractions? I will argue that, to answer this question, we must view LLMs through the lens of generalization. That is, we should consider the data that LLMs were trained on so…
-
FDS Special Seminar: Peiran Jin (Microsoft Research), “Nature Language Model: Deciphering the Language of Nature for Scientific Discovery”
Nature Language Model: Deciphering the Language of Nature for Scientific Discovery [https://arxiv.org/abs/2502.07527] Abstract: Foundation models have revolutionized natural language processing and artificial intelligence, significantly enhancing how machines comprehend and generate human languages. Inspired by the success of these foundation models, researchers have developed foundation models for individual scientific domains, including small molecules, materials, proteins, DNA,…
-
-
FDS Special Seminar: Yi R. (May) Fung (HKUST), “Scaling Human-Centric Trustworthy Foundation Model Reasoning”
Abstract: In recent years, language models have made significant advancements, achieving remarkable performance on a large variety of tasks, as well as promising zero-shot/few-shot capabilities, bolstered by model scaling and innovative training techniques. Despite the exciting progress, ensuring these models align with fundamental constitutional principles of promoting helpful, honest, and harmless information communication remains a…
-
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,…