← Search

Klara Kaleb

2 accepted papers

2026

StochasTok: Improving Fine-Grained Subword Understanding in LLMs

ICLR 2026poster

Subword-level understanding is integral to numerous tasks, including understanding multi-digit numbers, spelling mistakes, abbreviations, rhyming, and wordplay. Despite this, current large language models (LLMs) still struggle disproportionally with seemingly simple subword-level tasks, like countin…

Cited by 0SourcecodeScholar
2024

Feedback control guides credit assignment in recurrent neural networks

NeurIPS 2024poster

How do brain circuits learn to generate behaviour? While significant strides have been made in understanding learning in artificial neural networks, applying this knowledge to biological networks remains challenging. For instance, while backpropagation is known to perform accurate credit assignm…

Cited by 1SourcePDFScholar