Signals 4 · free daily AI digest

Diffusion Drafts, AR Verifies: Accelerating Document OCR with Self-Speculative Decoding

Paper recorded by Signals 4 on 2026-09-22 in cs.CL. Abstract reproduced from arXiv; link to the original below.

Published 2026-09-22 on arXiv · recorded by Signals 4 on 2026-09-23

Category: cs.CL · 自然语言处理 · first seen 2026-09-23

Abstract

Autoregressive OCR vision-language models accurately convert document images into text and structured markup, but require one sequential decoding step per output token, limiting inference speed. Unlike open-ended text generation, OCR outputs are strongly grounded in the input image, making diffusion-based parallel generation promising. However, when several tokens are predicted in one diffusion st

Read on arXiv →

#4 most recent of 227 cs.CL papers we have recorded · ↑ newer: Detecting GPT-Assisted Writing Using Interpretable Stylometric Feature · ↓ older: Knowledge Pull Requests for Continual Document Authoring
Cite this page: Diffusion Drafts, AR Verifies: Accelerating Document OCR with Self-Speculative Decoding: the #4 most recent of 227 cs.CL papers we have recorded (as of 2026-09-22). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/diffusion-drafts-ar-verifies-accelerating-document-ocr-with-self-speculative-dec.html
Free to quote with attribution to “Signals 4 (Signals API)”. Machine-readable: papers.json
Related: More cs.CL papers · arXiv signals · All papers · Today in AI
Get 4 AI signals a day by email — free.
Subscribe free → See all plans →
Get 4 AI signals a day by email — free
All models · All repos · By company · Daily editions