Dystruct formulates flexible-length generation in diffusion language models as a dynamic structural inference problem solved via Bayesian integration of local uncertainty and structural signals.
Kakade, Timothy Ngotiaoco, Sitan Chen, and Michael Samuel Albergo
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Dystruct: Dynamically Structured Diffusion Language Model Decoding via Bayesian Inference
Dystruct formulates flexible-length generation in diffusion language models as a dynamic structural inference problem solved via Bayesian integration of local uncertainty and structural signals.