← Search

Yana Veitsman

2 accepted papers

2025

Born a Transformer -- Always a Transformer? On the Effect of Pretraining on Architectural Abilities

NeurIPS 2025poster

Transformers have theoretical limitations in modeling certain sequence-to-sequence tasks, yet it remains largely unclear if these limitations play a role in large-scale pretrained LLMs, or whether LLMs might effectively overcome these constraints in practice due to the scale of both the models thems…

Cited by 0SourceScholar
2024

The Expressive Capacity of State Space Models: A Formal Language Perspective

NeurIPS 2024poster

Recently, recurrent models based on linear state space models (SSMs) have shown promising performance in language modeling (LM), competititve with transformers. However, there is little understanding of the in-principle abilities of such models, which could provide useful guidance to the search for…

Cited by 3SourcePDFScholar