AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

AR-Diffusion: Auto-Regressive Diffusion Model for Text Generation

Tong Wu, Zhihao Fan, Xiao Liu, Hai-Tao Zheng, Yeyun Gong, yelong shen, Jian Jiao, Juntao Li, zhongyu wei, Jian Guo, Nan Duan, Weizhu Chen

NeurIPS 2023 · Image generation › Autoregressive and latent generation · approach: Latent diffusion with learned tokenizers · 18 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add token-level position-dependent diffusion timesteps (vs GENIE with skipping) (ablation)AR-Diffusion · XSum testAVG-ROUGEImproved
use skipping mechanism instead of DDIM for fewer inference steps (ablation)AR-Diffusion · XSum testAVG-ROUGEImproved
anchor point n_e = 2N instead of 1N or 3N (ablation)AR-Diffusion · XSum testROUGEImproved
increase MBR candidates from k=50 to k=500AR-Diffusion · CNN/DailyMail testROUGE-2: 16.3 -> 17.1Improved
increase MBR candidates from k=50 to k=500AR-Diffusion · IWSLT14 De-En BLEUBLEU: 34.95 -> 35.62Improved
reduce inference steps from 20 to 2AR-Diffusion · XSum testROUGE-1: 30.99 -> 29.28Hurt
reduce inference steps from 20 to 2GENIE · XSum testROUGE-1: 28.33 -> 23.45Hurt
AR-Diffusion instead of GENIE at 20 stepsIWSLT14 De-En · IWSLT14 De-En (SeqDiffuSeq setting)BLEU: 30.08 -> 34.95Improved

Later papers that compared with this method

1 later accepted paper reports AR-Diffusion as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy