# Diffusion Language Models are Super Data Learners

arXiv: https://arxiv.org/abs/2511.03276 · HTML: https://mlsanity.com/paper/2511.03276/

## Key facts

- Cited by 48 papers in the map (data through 14 Oct 2026).
- Placed in Discrete and text diffusion, one of 14 directions in Diffusion models.
- Builds on 38 of its 45 references that are in the map.
- First posted on arXiv 5 Nov 2025.

## Placed in

- Diffusion models / [Discrete and text diffusion](https://mlsanity.com/diffusion/discrete-and-text-diffusion/)

## Builds on (most cited first, 30 of 38)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer](https://mlsanity.com/paper/1701.06538/) (2017)
- [Training Compute-Optimal Large Language Models](https://mlsanity.com/paper/2203.15556/) (2022)
- [The FineWeb Datasets: Decanting the Web for the Finest Text Data at Scale](https://mlsanity.com/paper/2406.17557/) (2024)
- [Large Language Diffusion Models](https://mlsanity.com/paper/2502.09992/) (2025)
- [Simple and Effective Masked Diffusion Language Models](https://mlsanity.com/paper/2406.07524/) (2024)
- [The RefinedWeb Dataset for Falcon LLM: Outperforming Curated Corpora with Web Data, and Web Data Only](https://mlsanity.com/paper/2306.01116/) (2023)
- [Discrete Diffusion Modeling by Estimating the Ratios of the Data Distribution](https://mlsanity.com/paper/2310.16834/) (2023)
- [GPT-NeoX-20B: An Open-Source Autoregressive Language Model](https://mlsanity.com/paper/2204.06745/) (2022)
- [Simplified and Generalized Masked Diffusion for Discrete Data](https://mlsanity.com/paper/2406.04329/) (2024)
- [Kimi K2: Open Agentic Intelligence](https://mlsanity.com/paper/2507.20534/) (2025)
- [Dream 7B: Diffusion Large Language Models](https://mlsanity.com/paper/2508.15487/) (2025)
- [Dolma: an Open Corpus of Three Trillion Tokens for Language Model Pretraining Research](https://mlsanity.com/paper/2402.00159/) (2024)
- [Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding](https://mlsanity.com/paper/2505.22618/) (2025)
- [Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Models](https://mlsanity.com/paper/2503.09573/) (2025)
- [Scaling Data-Constrained Language Models](https://mlsanity.com/paper/2305.16264/) (2023)
- [Your Absorbing Discrete Diffusion Secretly Models the Conditional Distributions of Clean Data](https://mlsanity.com/paper/2406.03736/) (2024)
- [OLMoE: Open Mixture-of-Experts Language Models](https://mlsanity.com/paper/2409.02060/) (2024)
- [LLaDA 1.5: Variance-Reduced Preference Optimization for Large Language Diffusion Models](https://mlsanity.com/paper/2505.19223/) (2025)
- [Mercury: Ultra-Fast Language Models Based on Diffusion](https://mlsanity.com/paper/2506.17298/) (2025)
- [DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation](https://mlsanity.com/paper/2506.20639/) (2025)
- [Seed Diffusion: A Large-Scale Diffusion Language Model with High-Speed Inference](https://mlsanity.com/paper/2508.02193/) (2025)
- [Rephrasing the Web: A Recipe for Compute and Data-Efficient Language Modeling](https://mlsanity.com/paper/2401.16380/) (2024)
- [Nemotron-CC: Transforming Common Crawl into a Refined Long-Horizon Pretraining Dataset](https://mlsanity.com/paper/2412.02595/) (2024)
- [Scaling Laws and Interpretability of Learning from Repeated Data](https://mlsanity.com/paper/2205.10487/) (2022)
- [OpenCoder: The Open Cookbook for Top-Tier Code Large Language Models](https://mlsanity.com/paper/2411.04905/) (2024)
- [To Repeat or Not To Repeat: Insights from Scaling LLM under Token-Crisis](https://mlsanity.com/paper/2305.13230/) (2023)
- [Perplexed by Perplexity: Perplexity-Based Data Pruning With Small Reference Models](https://mlsanity.com/paper/2405.20541/) (2024)

## Built on by (most cited first, 30 of 48)

- [Principled RL for Diffusion LLMs Emerges from a Sequence-Level Perspective](https://mlsanity.com/paper/2512.03759/) (2025)
- [Dream-VL & Dream-VLA: Open Vision-Language and Vision-Language-Action Models with Diffusion Language Model Backbone](https://mlsanity.com/paper/2512.22615/) (2025)
- [DMax: Aggressive Parallel Decoding for dLLMs](https://mlsanity.com/paper/2604.08302/) (2026)
- [Improved Large Language Diffusion Models](https://mlsanity.com/paper/2606.25331/) (2026)
- [Stable-DiffCoder: Pushing the Frontier of Code Diffusion Large Language Model](https://mlsanity.com/paper/2601.15892/) (2026)
- [Omni-Diffusion: Unified Multimodal Understanding and Generation with Masked Discrete Diffusion](https://mlsanity.com/paper/2603.06577/) (2026)
- [Data-Efficient Autoregressive-to-Diffusion Language Models via On-Policy Distillation](https://mlsanity.com/paper/2606.06712/) (2026)
- [Where-to-Unmask: Ground-Truth-Guided Unmasking Order Learning for Masked Diffusion Language Models](https://mlsanity.com/paper/2602.09501/) (2026)
- [Data Repetition Beats Data Scaling in Long-CoT Supervised Fine-Tuning](https://mlsanity.com/paper/2602.11149/) (2026)
- [MinerU-Diffusion: Rethinking Document OCR as Inverse Rendering via Diffusion Decoding](https://mlsanity.com/paper/2603.22458/) (2026)
- [When to Commit? Towards Variable-Size Self-Contained Blocks for Discrete Diffusion Language Models](https://mlsanity.com/paper/2604.23994/) (2026)
- [DiffuMamba: High-Throughput Diffusion LMs with Mamba Backbone](https://mlsanity.com/paper/2511.15927/) (2025)
- [FLARE: Diffusion for Hybrid Language Model](https://mlsanity.com/paper/2606.01774/) (2026)
- [Entropy-Guided Token Dropout: Training Autoregressive Language Models with Limited Domain Data](https://mlsanity.com/paper/2512.23422/) (2025)
- [DreamReasoner-8B: Block-Size Curriculum Learning for Diffusion Reasoning Models](https://mlsanity.com/paper/2606.19257/) (2026)
- [On the Role of Discreteness in Diffusion LLMs](https://mlsanity.com/paper/2512.22630/) (2025)
- [Training-Trajectory-Aware Token Selection](https://mlsanity.com/paper/2601.10348/) (2026)
- [Next-Scale Autoregressive Models for Text-to-Motion Generation](https://mlsanity.com/paper/2604.03799/) (2026)
- [Nexus: Same Pretraining Loss, Better Downstream Generalization via Common Minima](https://mlsanity.com/paper/2604.09258/) (2026)
- [Demystifying Training-Time Augmentation for Data-Constrained Language Model Pretraining](https://mlsanity.com/paper/2606.16246/) (2026)
- [Top 10 Open Challenges Steering the Future of Diffusion Language Model and Its Variants](https://mlsanity.com/paper/2601.14041/) (2026)
- [Causal Autoregressive Diffusion Language Model](https://mlsanity.com/paper/2601.22031/) (2026)
- [DIFFA-2: A Practical Diffusion Large Language Model for General Audio Understanding](https://mlsanity.com/paper/2601.23161/) (2026)
- [FOCUS: DLLMs Know How to Tame Their Compute Bound](https://mlsanity.com/paper/2601.23278/) (2026)
- [DICE: Diffusion Large Language Models Excel at Generating CUDA Kernels](https://mlsanity.com/paper/2602.11715/) (2026)
- [Locally Coherent Parallel Decoding in Diffusion Language Models](https://mlsanity.com/paper/2603.20216/) (2026)
- [Fast Byte Latent Transformer](https://mlsanity.com/paper/2605.08044/) (2026)
- [Data-Constrained Language Model Pretraining: Improved Regularization and Scaling Laws](https://mlsanity.com/paper/2606.06888/) (2026)
- [Sink-Aware Pruning for Diffusion Language Models](https://mlsanity.com/paper/2602.17664/) (2026)
- [On the Trainability of Masked Diffusion Language Models via Blockwise Locality](https://mlsanity.com/paper/2604.24832/) (2026)

## Abstract (arXiv)

Under strictly controlled pre-training settings, we observe a Crossover: when unique data is limited, diffusion language models (DLMs) consistently surpass autoregressive (AR) models by training for more epochs. The crossover shifts later with more or higher-quality data, earlier with larger models, and persists across dense and sparse architectures. We attribute the gains to three compounding factors: (1) any-order modeling, (2) super-dense compute from iterative bidirectional denoising, and (3) built-in Monte Carlo augmentation; input or parameter noise improves AR under data constraint but cannot close the gap. At scale, a 1.7B DLM trained with a ~1.5T-token compute budget on 10B unique Python tokens overtakes an AR coder trained with strictly matched settings. In addition, a 1B-parameter DLM achieves > 56% accuracy on HellaSwag and > 33% on MMLU using only 1B tokens, without any special tricks, just by repeating standard pre-training data. We also show that rising validation cross-entropy does not imply degraded downstream performance in this regime.