Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
NeuroSonic: Conditional Flow Matching for EEG-to-Speech Reconstruction
Wenhao Gao, Yifan Wang, Yijia Ma +3
Reconstructing continuous speech from scalp electroencephalography (EEG) remains fundamentally challenging. EEG provides a weak, spatially diffuse, and highly variable measurement…
cs.LG2026
Neural Estimation of Pairwise Mutual Information in Masked Discrete Sequence Models
Jai Sharma, Yifan Wang, Bryan Li
Understanding dependencies between variables is critical for interpretability and efficient generation in masked diffusion models (MDMs), yet these models primarily expose marginal…