← Search

Thomas Marshall

2 accepted papers

2025

Do Transformer Interpretability Methods Transfer to RNNs?

AAAI 2025technical

Recent advances in recurrent neural network architectures, such as Mamba and RWKV, have enabled RNNs to match or exceed the performance of equal-size transformers in terms of language modeling perplexity and downstream evaluations, suggesting that future systems may be built on completely new archit…

2025

Parameterized Synthetic Text Generation with SimpleStories

NeurIPS 2025poster

We present SimpleStories, a large synthetic story dataset in simple language, consisting of 2 million samples each in English and Japanese. Through parameterizing prompts at multiple levels of abstraction, we achieve control over story characteristics at scale, inducing syntactic and semantic divers…

Cited by 0SourcecodeScholar