SOURCE-LINKED INTELLIGENCE

CARVE: Verified Expansion for Variable-Length Generation in Diffusion Language Models

arXiv · AI, language, vision and robotics · article · Aug 31, 2026 · UTC

Masked diffusion language models predict tokens from a partially observed response canvas, enabling bidirectional conditioning and parallel token refinement. Yet standard masked-diffusion decoders use a rigid inference interface: the number of masked positions allocated to the answer is fixed before generation begins. Choosing this length is difficult. A short canvas can truncate reasoning or code, while a long canvas wastes computation and can perturb denoising. We introduce CARVE (Counterfactual-Aware Reveal with Verified Expansion), a training-free variable-length algorithm for masked diffu

Read original source ↗ Open in workspace

recordType

paper

region

Global