collaborators

6 papers

cs.LG2026

Why Are Linear RNNs More Parallelizable?

William Merrill, Hongjian Jiang, Yanhong Li +2

The community is increasingly exploring linear RNNs (LRNNs) as language models, motivated by their expressive power and parallelizability. While prior work establishes the expressi…

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.CL2026

Probability Distributions Computed by Autoregressive Transformers

Andy Yang, Anej Svete, Jiaoda Li +4

Most expressivity results for transformers treat them as language recognizers -- devices that accept or reject strings -- rather than as they are used in practice: as language mode…

cs.FL2026

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.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.LO2026

Fast Ramsey Quantifier Elimination in LIRA (with applications to liveness checking)

Kilian Lichtner, Pascal Bergsträßer, Moses Ganardi +2

Ramsey quantifiers have recently been proposed as a unified framework for handling properties of interests in program verification involving proofs in the form of infinite cliques,…