There is a growing interest in the ability of neural networks to execute algorithmic tasks (e.g., arithmetic, summary statistics, and sorting). The goal of this work is to better understand the role o...

Co-developed by alum Ryan Yen, Code Shaping can transform coding beyond the keyboard.

In this work we revisit the arithmetic and bit complexity of Hermitian eigenproblems. We first provide an analysis for the divide-and-conquer tridiagonal eigensolver of Gu and Eisenstat [GE95] in the ...

We show that transformer-based large language models are computationally universal when augmented with an external memory. Any deterministic language model that conditions on strings of bounded length...

Neural networks (NNs), despite their success and wide adoption, still struggle to extrapolate out-of-distribution (OOD), i.e., to inputs that are not well-represented by their training dataset. Addres...

Διαλέξεις Τεχνητής Νοημοσύνης και Μηχανικής Μάθησης: https://caramanis.github.io/MachineLearningClass/ Καλωσορίσατε στο μάθημα τεχνητής νοημοσύνης και μηχανι...

OpenAI’s o3 model aces the "Abstraction and Reasoning Corpus" — but what does it mean?

It's been an odd week for the academic publisher MDPI. On 16th December, Finland's Publication Forum (known as JUFO) announced that from J...

These videos are live recordings, minimally edited, of 56 lectures on graph theory that I gave at Hamburg University in 2023/24. They are based on the 6th edition of my Graph Theory book, which is ava...

Artificial Expert Intelligence (AEI) seeks to transcend the limitations of both Artificial General Intelligence (AGI) and narrow AI by integrating domain-specific expertise with critical, precise reas...

This is an exciting time for mathematics, as new technologies for mathematical reasoning provide novel opportunities for mathematical research, communication, and discovery. Mathlib, a library of form...