Primal-dual guided decoding casts constrained discrete diffusion as a KL-regularized optimization solved online with adaptive Lagrangian multipliers to satisfy constraints while staying close to the unconstrained model distribution.
Incremental sequence classification with temporal consistency
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Primal-Dual Guided Decoding for Constrained Discrete Diffusion
Primal-dual guided decoding casts constrained discrete diffusion as a KL-regularized optimization solved online with adaptive Lagrangian multipliers to satisfy constraints while staying close to the unconstrained model distribution.