5 citations · 5 across the 3 of their papers we have counts for
4 papers
Group-Invariant Statistics Determine Embedding Geometry: Harmonic Analysis of Representations from Bach to the Night Sky
Liam Storan, Andreas Tolias, Nina Miolane
The representations that language models learn for concepts such as months, weekdays, and places display consistent geometric structure: circles and saddle-shaped "Pringle" manifol…
From Kepler to Newton: Inductive Biases Guide Learned World Models in Transformers
Ziming Liu, Sophia Sanborn, Surya Ganguli +1
Can general-purpose AI architectures go beyond prediction to discover the physical laws governing the universe? True intelligence relies on "world models" -- causal abstractions th…
A note on the Muckenhoupt class
Eleftherios N. Nikolidakis, Andreas G. Tolias
We provide a direct proof of the best possible reverse Holder inequality satisfied by every weight defined on the interval with A1-constant equal to c > 1.
NeuroAI for AI Safety
Patrick Mineault, Niccolò Zanichelli, Joanne Zichen Peng +12
As AI systems become increasingly powerful, the need for safe AI has become more pressing. Humans are an attractive model for AI safety: as the only known agents capable of general…