Saved in:
Bibliographic Details
Main Authors: Miao, Tongyuan, Huang, Gary, Han, Kai Jun, Jiang, Annie
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2512.19004
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914213888262144
author Miao, Tongyuan
Huang, Gary
Han, Kai Jun
Jiang, Annie
author_facet Miao, Tongyuan
Huang, Gary
Han, Kai Jun
Jiang, Annie
contents Diffusion Large Language Models (DLLMs) enable fully parallel token decoding but often remain impractical at inference time due to the many denoising iterations required to refine an information-free, fully masked initialization into coherent text. Most existing acceleration methods focus on traversing this generative trajectory more efficiently via improved solvers or sampling strategies. We advance a complementary perspective: shorten the trajectory itself by starting closer to the target distribution through context-aware initialization. We propose a training-free interface that injects prompt-conditioned priors from a lightweight auxiliary model into the diffusion initialization, and instantiate it with two mechanisms: discrete token injection and representation-level embedding interpolation. Because injected priors can be imperfect and unmask-only decoding can over-commit early, we also introduce a simple confidence-based remasking mechanism as a form of prior skepticism. Preliminary evidence on GSM8K suggests that context-aware initialization can substantially reduce denoising iterations (about 35\% fewer function evaluations in our setting), while also exposing a key open challenge: naive warm-starting can degrade final accuracy relative to strong diffusion baselines. We use these findings to motivate a research agenda around calibration, revision mechanisms, and representation alignment for reliable warm-started diffusion decoding.
format Preprint
id arxiv_https___arxiv_org_abs_2512_19004
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Context-Aware Initialization for Reducing Generative Path Length in Diffusion Language Models
Miao, Tongyuan
Huang, Gary
Han, Kai Jun
Jiang, Annie
Computation and Language
Artificial Intelligence
Machine Learning
Diffusion Large Language Models (DLLMs) enable fully parallel token decoding but often remain impractical at inference time due to the many denoising iterations required to refine an information-free, fully masked initialization into coherent text. Most existing acceleration methods focus on traversing this generative trajectory more efficiently via improved solvers or sampling strategies. We advance a complementary perspective: shorten the trajectory itself by starting closer to the target distribution through context-aware initialization. We propose a training-free interface that injects prompt-conditioned priors from a lightweight auxiliary model into the diffusion initialization, and instantiate it with two mechanisms: discrete token injection and representation-level embedding interpolation. Because injected priors can be imperfect and unmask-only decoding can over-commit early, we also introduce a simple confidence-based remasking mechanism as a form of prior skepticism. Preliminary evidence on GSM8K suggests that context-aware initialization can substantially reduce denoising iterations (about 35\% fewer function evaluations in our setting), while also exposing a key open challenge: naive warm-starting can degrade final accuracy relative to strong diffusion baselines. We use these findings to motivate a research agenda around calibration, revision mechanisms, and representation alignment for reliable warm-started diffusion decoding.
title Context-Aware Initialization for Reducing Generative Path Length in Diffusion Language Models
topic Computation and Language
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2512.19004