Info-Gain Sampler improves MDM decoding by using bidirectional information gain to reduce cumulative uncertainty, outperforming greedy samplers on reasoning accuracy and creative writing tasks.
Formal Definitions of Baseline Samplers To provide a rigorous comparison, we formalize the action selection mechanism for each baseline sampler
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Improving Sampling for Masked Diffusion Models via Information Gain
Info-Gain Sampler improves MDM decoding by using bidirectional information gain to reduce cumulative uncertainty, outperforming greedy samplers on reasoning accuracy and creative writing tasks.