mlsanityData to 14 Oct 2026

Seed Diffusion: A Large-Scale Diffusion Language Model with High-Speed Inference

arXiv 2508.02193 ↗First posted 4 Aug 2025cs.CL cs.LGcited by 178

On the map: Diffusion models → Discrete and text diffusion

Abstract (arXiv)

We present Seed Diffusion Preview, a large-scale language model based on discrete-state diffusion, offering remarkably fast inference speed. Thanks to non-sequential, parallel generation, discrete diffusion models provide a notable speedup to mitigate the inherent latency of token-by-token decoding, as demonstrated recently (e.g., Mercury Coder, Gemini Diffusion). Seed Diffusion Preview achieves an inference speed of 2,146 token/s over H20 GPUs while maintaining competitive performance across a sweep of standard code evaluation benchmarks, significantly faster than contemporary Mercury and Gemini Diffusion, establishing new state of the art on the speed-quality Pareto frontier for code models.

Key facts. Cited by 178 papers in the map (data through 14 Oct 2026). Placed in Discrete and text diffusion, one of 14 directions in Diffusion models. Builds on 28 of its 32 references that are in the map. First posted on arXiv 4 Aug 2025.

Builds on

28 of 32 references.

Closest ancestors · 8

Same direction, newest first

  1. 2025Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Models12 Mar
  2. 2025Large Language Diffusion Models14 Feb
  3. 2024Simple and Effective Masked Diffusion Language Models11 Jun
  4. 2024Simplified and Generalized Masked Diffusion for Discrete Data6 Jun
  5. 2024Your Absorbing Discrete Diffusion Secretly Models the Conditional Distributions of Clean Data6 Jun
  6. 2023Likelihood-Based Diffusion Language Models30 May
  7. 2022Continuous diffusion for categorical data28 Nov
  8. 2021Autoregressive Diffusion Models5 Oct

Other references · 20

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
  3. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,101
  4. 2022Video Diffusion Modelscited by 2,305
  5. 2024LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Codecited by 2,004
  6. 2021Structured Denoising Diffusion Models in Discrete State-Spacescited by 1,719
  7. 2024BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructionscited by 546
  8. 2017Non-Autoregressive Neural Machine Translationcited by 463
  9. 2019Monte Carlo Gradient Estimation in Machine Learningcited by 283
  10. 2025Mercury: Ultra-Fast Language Models Based on Diffusioncited by 235
  11. 2022Multi-lingual Evaluation of Code Generation Modelscited by 159
  12. 2020Glancing Transformer for Non-Autoregressive Neural Machine Translationcited by 103
8 more
  1. 2023Bayesian Flow Networkscited by 63
  2. 2025Seed-Coder: Let the Code Model Curate Data for Itselfcited by 49
  3. 2023Can It Edit? Evaluating the Ability of Large Language Models to Follow Code Editing Instructionscited by 48
  4. 2024ACDiT: Interpolating Autoregressive Conditional Modeling and Diffusion Transformercited by 45
  5. 2022Directed Acyclic Transformer for Non-Autoregressive Machine Translationcited by 44
  6. 2024NaturalCodeBench: Examining Coding Performance Mismatch on HumanEval and Natural User Promptscited by 19
  7. 2020Do You Have the Right Scissors? Tailoring Pre-trained Language Models via Monte-Carlo Methodscited by 5
  8. 2022Diffusion Glancing Transformer for Parallel Sequence to Sequence Learningcited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 68; 2026: 110.

178 papers.

Sort:

By area:

  1. 2025A Survey of Reinforcement Learning for Large Reasoning Modelscited by 180
  2. 2025LLaDA2.0: Scaling Up Diffusion Language Models to 100Bcited by 166
  3. 2025SDAR: A Synergistic Diffusion-AutoRegression Paradigm for Scalable Sequence Generationcited by 129
  4. 2025A Survey on Diffusion Language Modelscited by 78
  5. 2025Diffusion Language Models Know the Answer Before Decodingcited by 70
  6. 2025dParallel: Learnable Parallel Decoding for dLLMscited by 65
  7. 2026LLaDA2.1: Speeding Up Text Diffusion via Token Editingcited by 54
  8. 2025Any-Order Flexible Length Masked Diffusioncited by 51
  9. 2025Diffusion Language Models are Super Data Learnerscited by 48
  10. 2026ELF: Embedded Language Flowscited by 45
  11. 2025ParallelBench: Understanding the Trade-offs of Parallel Decoding in Diffusion LLMscited by 43
  12. 2025DPad: Efficient Diffusion Language Models with Suffix Dropoutcited by 39
38 more
  1. 2025Don't Settle Too Early: Self-Reflective Remasking for Diffusion Language Modelscited by 37
  2. 2025dInfer: An Efficient Inference Framework for Diffusion Language Modelscited by 37
  3. 2026d3LLM: Ultra-Fast Diffusion LLM using Pseudo-Trajectory Distillationcited by 37
  4. 2025Continuously Augmented Discrete Diffusion model for Categorical Generative Modelingcited by 34
  5. 2025Principled RL for Diffusion LLMs Emerges from a Sequence-Level Perspectivecited by 34
  6. 2025Improving Reasoning for Diffusion Language Models via Group Diffusion Policy Optimizationcited by 33
  7. 2025Efficient-DLM: From Autoregressive to Diffusion Language Models, and Beyond in Speedcited by 33
  8. 2025MDPO: Overcoming the Training-Inference Divide of Masked Diffusion Language Modelscited by 32
  9. 2025AdaBlock-dLLM: Semantic-Aware Diffusion LLM Inference via Adaptive Block Sizecited by 31
  10. 2025A Survey on Parallel Text Generation: From Parallel Decoding to Diffusion Language Modelscited by 30
  11. 2025Learning Unmasking Policies for Diffusion Language Modelscited by 30
  12. 2025LaDiR: Latent Diffusion Enhances LLMs for Text Reasoningcited by 29
  13. 2025d2: Improving Reasoning in Diffusion Language Models via Trajectory Likelihood Estimationcited by 27
  14. 2026Scaling Beyond Masked Diffusion Language Modelscited by 27
  15. 2025Training Optimal Large Diffusion Language Modelscited by 25
  16. 2025Encoder-Decoder Diffusion Language Models for Efficient Training and Inferencecited by 24
  17. 2026Nemotron-Labs-Diffusion: A Tri-Mode Language Model Unifying Autoregressive, Diffusion, and Self-Speculation Decodingcited by 24
  18. 2025Quantization Meets dLLMs: A Systematic Study of Post-training Quantization for Diffusion LLMscited by 23
  19. 2025Set Block Decoding is a Language Model Inference Acceleratorcited by 23
  20. 2025From Bits to Rounds: Parallel Decoding with Exploration for Diffusion Language Modelscited by 23
  21. 2025Improving Discrete Diffusion Unmasking Policies Beyond Explicit Reference Policiescited by 22
  22. 2025Diffusion LLM with Native Variable Generation Lengths: Let [EOS] Lead the Waycited by 22
  23. 2025Structuring The Future: Diffusion LLM Speculative Decoding via Calibrated Draft Graphscited by 21
  24. 2025Accelerating Diffusion LLM Inference via Local Determinism Propagationcited by 21
  25. 2025CDLM: Consistency Diffusion Language Models For Faster Samplingcited by 21
  26. 2025Enhancing Reasoning for Diffusion LLMs via Distribution Matching Policy Optimizationcited by 20
  27. 2025Sequential Diffusion Language Modelscited by 19
  28. 2025Free Draft-and-Verification: Toward Lossless Parallel Decoding for Diffusion Large Language Modelscited by 19
  29. 2025DiFFPO: Training Diffusion LLMs to Reason Fast and Furious via Reinforcement Learningcited by 19
  30. 2026Continuous Diffusion Scales Competitively with Discrete Diffusion for Languagecited by 19
  31. 2026The Flexibility Trap: Rethinking the Value of Arbitrary Order in Diffusion Language Modelscited by 18
  32. 2026Confidence-Based Decoding is Provably Efficient for Diffusion Language Modelscited by 18
  33. 2026DMax: Aggressive Parallel Decoding for dLLMscited by 18
  34. 2025Taming Masked Diffusion Language Models via Consistency Trajectory Reinforcement Learning with Fewer Decoding Stepcited by 17
  35. 2025d-TreeRPO: Towards More Reliable Policy Optimization for Diffusion Language Modelscited by 17
  36. 2025Exploring the Potential of Diffusion Large Language Models in Code Generationcited by 16
  37. 2025Ultra-Fast Language Generation via Discrete Diffusion Divergence Instructcited by 16
  38. 2025Planner Aware Path Learning in Diffusion Language Models Trainingcited by 14

50 most cited of 178 All 178 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024Speculative Diffusion Decoding: Accelerating Language Generation through Diffusion
  2. 2026Set Diffusion: Interpolating Token Orderings Between Autoregression and Diffusion for Fast and Flexible Decoding
  3. 2025Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding
  4. 2026Accelerating Masked Diffusion Large Language Models: A Survey of Efficient Inference Techniques
  5. 2025Dream 7B: Diffusion Large Language Models
  6. 2026PSD: Pushing the Pareto Frontier of Diffusion LLMs via Parallel Speculative Decoding
  7. 2026D^2SD: Accelerating Speculative Decoding with Dual Diffusion Draft Models
  8. 2026Mean-Field Parallel Decoding for Discrete Diffusion Language Models