← Search

Berkay Döner

2 accepted papers

2025

LUNA: Efficient and Topology-Agnostic Foundation Model for EEG Signal Analysis

NeurIPS 2025poster

Electroencephalography (EEG) offers a non-invasive lens into human brain activity, but building large‐scale models is hampered by $\textit{topological heterogeneity}$: each public corpus defines its own electrode layout, limiting generalization. We introduce $\textbf{LUNA}$ ($\textbf{L}$atent $\text…

Cited by 0SourcecodeScholar
2024

Sketch-Guided Constrained Decoding for Boosting Blackbox Large Language Models without Logit Access

ACL 2024short

Constrained decoding, a technique for enforcing constraints on language model outputs, offers a way to control text generation without retraining or architectural modifications. Its application is, however, typically restricted to models that give users access to next-token distributions (usually vi…