← Search

Anthony Lin

2 accepted papers

2026

Length Generalization Bounds for Transformers

ICML 2026poster

Length generalization is a key property of a learning algorithm that enables it to make correct predictions on inputs of unbounded length, given finite training data. To provide such a guarantee, one needs to be able to compute a length generalization bound, beyond which the model is guaranteed to g…

Cited by 0SourceScholar