Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Fathi, Nima, Scholak, Torsten, Noël, Pierre-André
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2504.06416
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866916992074645504
author Fathi, Nima
Scholak, Torsten
Noël, Pierre-André
author_facet Fathi, Nima
Scholak, Torsten
Noël, Pierre-André
contents We present significant extensions to diffusion-based sequence generation models, blurring the line with autoregressive language models. We introduce hyperschedules, which assign distinct noise schedules to individual token positions, generalizing both autoregressive models (e.g., GPT) and conventional diffusion models (e.g., SEDD, MDLM) as special cases. Second, we propose two hybrid token-wise noising processes that interpolate between absorbing and uniform processes, enabling the model to fix past mistakes, and we introduce a novel inference algorithm that leverages this new feature in a simplified context inspired from MDLM. To support efficient training and inference, we design attention masks compatible with KV-caching. Our methods achieve state-of-the-art perplexity and generate diverse, high-quality sequences across standard benchmarks, suggesting a promising path for autoregressive diffusion-based sequence generation. See code and resources at https://hdlm-colm.github.io/
format Preprint
id arxiv_https___arxiv_org_abs_2504_06416
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Unifying Autoregressive and Diffusion-Based Sequence Generation
Fathi, Nima
Scholak, Torsten
Noël, Pierre-André
Machine Learning
We present significant extensions to diffusion-based sequence generation models, blurring the line with autoregressive language models. We introduce hyperschedules, which assign distinct noise schedules to individual token positions, generalizing both autoregressive models (e.g., GPT) and conventional diffusion models (e.g., SEDD, MDLM) as special cases. Second, we propose two hybrid token-wise noising processes that interpolate between absorbing and uniform processes, enabling the model to fix past mistakes, and we introduce a novel inference algorithm that leverages this new feature in a simplified context inspired from MDLM. To support efficient training and inference, we design attention masks compatible with KV-caching. Our methods achieve state-of-the-art perplexity and generate diverse, high-quality sequences across standard benchmarks, suggesting a promising path for autoregressive diffusion-based sequence generation. See code and resources at https://hdlm-colm.github.io/
title Unifying Autoregressive and Diffusion-Based Sequence Generation
topic Machine Learning
url https://arxiv.org/abs/2504.06416