A neural estimator trained on self-computed mutual information from masked diffusion model hidden states predicts the full pairwise MI matrix in one forward pass to enable faster parallel decoding of conditionally independent variables.
arXiv preprint arXiv:2306.11363 , year=
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Neural Estimation of Pairwise Mutual Information in Masked Discrete Sequence Models
A neural estimator trained on self-computed mutual information from masked diffusion model hidden states predicts the full pairwise MI matrix in one forward pass to enable faster parallel decoding of conditionally independent variables.