Diffusion large language models (dLLMs) can generate multiple tokens in parallel, but often require many decoding rounds to complete a response. Efficient generation depends not only on which tokens are easy to predict, but also on how committing to them helps predict the remaining positions. A highly predictable token may provide little useful context, while revealing a less predictable token can help several other positions become predictable sooner. We propose dSpark, a new schedule distillation-based framework for learning when to commit tokens for faster diffusion language generation. To achieve this, we construct unmasking schedules that prioritize tokens whose reveal makes other positions easier to predict, reducing uncertainty earlier in decoding. We then distill these schedules into the model to enable faster parallel sampling, with a KL-divergence regularizer to help preserve generation quality. We extensively evaluate our approach across mathematical reasoning and code generation tasks. On GSM8K, our method achieves remarkable 10.12$\times$ and 5.12$\times$ speedups over the various baselines on LLaDA-8B-Instruct and Dream-7B-Instruct, respectively, while maintaining superior task performance. Our code is available at https://github.com/VILA-Lab/dSpark.
Before the Token Commits: Trajectory-Level Benchmarking of Visual Hallucinations in Diffusion VLMs
Nanjing University of Aeronautics and Astronautics（南京航空航天大学）；State Key Laboratory of Ocean Sensing, ZJU-Hangzhou Global Scientific and Technological Innovation Center, Zhejiang University（浙江大学杭州国际科创中心海洋感知全国重点实验室）；Security Capability Center（360安全能力中心）
University of California, San Diego（加州大学圣地亚哥分校）；Adobe Research（Adobe研究）；The University of New South Wales（新南威尔士大学）；CSIRO’s Data61（澳大利亚联邦科学与工业研究组织的数据61）
