IPR improves valid solution rates on MNIST Sudoku from 55.8% to 75.0% by iteratively refining partial regions in sequential diffusion models without external verifiers or reward models.
Fine-tuning masked diffusion for provable self-correction
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2026 4verdicts
UNVERDICTED 4representative citing papers
Token-to-Mask remasking improves self-correction in diffusion LLMs by resetting erroneous commitments to masks rather than overwriting them, yielding +13.33 points on AIME 2025 and +8.56 on CMATH.
CoDiLA adds a compact auxiliary AR model on diffusion latents to enforce local sequential validity during parallel token sampling in discrete diffusion language models.
Discrete Stochastic Localization lets a single trained network support an entire family of per-token SNR paths for discrete sequence generation, with masked diffusion as a special case, and improves MAUVE scores when fine-tuning pretrained checkpoints.
citing papers explorer
-
Inference-Time Scaling in Diffusion Models through Iterative Partial Refinement
IPR improves valid solution rates on MNIST Sudoku from 55.8% to 75.0% by iteratively refining partial regions in sequential diffusion models without external verifiers or reward models.
-
Remask, Don't Replace: Token-to-Mask Refinement in Diffusion Large Language Models
Token-to-Mask remasking improves self-correction in diffusion LLMs by resetting erroneous commitments to masks rather than overwriting them, yielding +13.33 points on AIME 2025 and +8.56 on CMATH.
-
Locally Coherent Parallel Decoding in Diffusion Language Models
CoDiLA adds a compact auxiliary AR model on diffusion latents to enforce local sequential validity during parallel token sampling in discrete diffusion language models.
-
Discrete Stochastic Localization for Non-autoregressive Generation
Discrete Stochastic Localization lets a single trained network support an entire family of per-token SNR paths for discrete sequence generation, with masked diffusion as a special case, and improves MAUVE scores when fine-tuning pretrained checkpoints.