activity
20242026
collaborators

5 papers

cs.LG2026

Length Generalization for Transformers via Compression

Georg Zetzsche, Hongjian Jiang, Andy Yang +4

Recent advancements in transformer length generalization theory enable us to reliably predict when a transformer can learn to solve a task. In particular, the C-RASP hypothesis (a…

cs.LG2026

The Polynomial Counting Capabilities of Message Passing Neural Networks

Marco Sälzer, Pascal Bergsträßer, Anthony W. Lin

The counting power of Message Passing Neural Networks (MPNN) has been the subject of many recent papers, showing that they can express logic that involves counting up to a threshol…

cs.LG2026

Length Generalization Bounds for Transformers

Andy Yang, Pascal Bergsträßer, Georg Zetzsche +2

Length generalization is a key property of a learning algorithm that enables it to make correct predictions on inputs of any length, given finite training data. To provide such a g…

cs.FL2025

Transformers are Inherently Succinct

Pascal Bergsträßer, Ryan Cotterell, Anthony W. Lin

We study succinctness as a measure of the expressive power of transformers. Succinctness -- how compactly a formalism can describe a language relative to other formalisms -- is a c…

cs.FL2024

The Power of Hard Attention Transformers on Data Sequences: A Formal Language Theoretic Perspective

Pascal Bergsträßer, Chris Köcher, Anthony Widjaja Lin +1

Formal language theory has recently been successfully employed to unravel the power of transformer encoders. This setting is primarily applicable in Natural Language Processing (NL…