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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add token-level position-dependent diffusion timesteps (vs GENIE with skipping) (ablation) | AR-Diffusion · XSum test | AVG-ROUGE | Improved |
| use skipping mechanism instead of DDIM for fewer inference steps (ablation) | AR-Diffusion · XSum test | AVG-ROUGE | Improved |
| anchor point n_e = 2N instead of 1N or 3N (ablation) | AR-Diffusion · XSum test | ROUGE | Improved |
| increase MBR candidates from k=50 to k=500 | AR-Diffusion · CNN/DailyMail test | ROUGE-2: 16.3 -> 17.1 | Improved |
| increase MBR candidates from k=50 to k=500 | AR-Diffusion · IWSLT14 De-En BLEU | BLEU: 34.95 -> 35.62 | Improved |
| reduce inference steps from 20 to 2 | AR-Diffusion · XSum test | ROUGE-1: 30.99 -> 29.28 | Hurt |
| reduce inference steps from 20 to 2 | GENIE · XSum test | ROUGE-1: 28.33 -> 23.45 | Hurt |
| AR-Diffusion instead of GENIE at 20 steps | IWSLT14 De-En · IWSLT14 De-En (SeqDiffuSeq setting) | BLEU: 30.08 -> 34.95 | Improved |
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.
- Smoothie: Smoothing Diffusion on Token Embeddings for Text Generation (ICML 2026 · better on 1 of 1 shared result)
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.
- GENIE — GENIE: Higher-Order Denoising Diffusion Solvers (NeurIPS 2022) · better on 2 of 2 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
- Energy-Based Diffusion Language Models for Text Generation (ICLR 2025 · similarity 0.92)
- Scaling Diffusion Language Models via Adaptation from Autoregressive Models (ICLR 2025 · similarity 0.92)
- Breaking AR’s Sampling Bottleneck: Provable Acceleration via Diffusion Language Models (NeurIPS 2025 · similarity 0.91)
- Fast and Fluent Diffusion Language Models via Convolutional Decoding and Rejective Fine-tuning (NeurIPS 2025 · similarity 0.90)
- Simple and Effective Masked Diffusion Language Models (NeurIPS 2024 · similarity 0.90)
- Anchored Diffusion Language Model (NeurIPS 2025 · similarity 0.89)
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.
