| title | BYOD: Build Your Own DLM - Efficient Autoregressive-to-Diffusion Language Model Conversion |
|---|---|
| authors | Ruurd J. A. Kuiper, Robert A. Bagheri |
| date | 2026-10-30 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2610.41574 |
| affiliation | University Medical Center Utrecht |
| upvotes | 8 (Hugging Face Daily Papers, 2026-11-04) |
| links | abs pdf hf code |
| cite | |
| abstract | Unlike autoregressive (AR) models, diffusion language models (DLMs) permit parallel token updates, flexible generation, and bidirectional attention, but leading systems rely on costly pretraining or full-model fine-tuning. We present Build Your Own DLM (BYOD), a generalizable LoRA-only recipe for parameter-efficient AR-to-DLM conversion. Without architecture-specific tuning, BYOD induces diffusion generation in Gemma 2 9B, Llama 3.1 8B, Qwen2.5 7B, and Ministral 8B; to our knowledge, this is the first reported AR-to-DLM conversion of a Mistral model. The adapters comprise 4.1-5.8% of final parameters while every base-model parameter remains frozen; each 25,000-iteration conversion needs at most 102.4M tokens, processed in 3.1-4.0 hours on one Google Colab GPU. All four models generate from fully masked sequences, use bidirectional context in a controlled attention test, and retain substantial parent-model knowledge. BYOD-Gemma is the strongest BYOD conversion on our nine-task evaluation, reaching 50.6% average accuracy compared with 51.9% for LLaDA 8B Instruct in the same harness. Open-generation quality at low network function evaluation (NFE) budgets remains the principal limitation: BYOD perplexity is 8.3-11.1 versus 4.1 for LLaDA and 2.2-3.0 for the AR parents when generating 128 tokens in 64 steps. To enable further experimentation and inspection, we provide a standalone training and evaluation implementation and interactive demos for all four conversions. BYOD thus provides a practical route for extending diffusion generation to other existing model families while identifying the gap that efficient conversion must next close. |
bibtex
@misc{kuiper2026byod,
title={BYOD: Build Your Own DLM - Efficient Autoregressive-to-Diffusion Language Model Conversion},
author={Ruurd J. A. Kuiper and Robert A. Bagheri},
year={2026},
eprint={2610.41574},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2610.41574}
}