mlsanityData to 13 Oct 2026

OneFlow: Concurrent Mixed-Modal and Interleaved Generation with Edit Flows

arXiv 2510.03506 ↗First posted 3 Oct 2025cs.AIcited by 17

Not on the map. Why?

Abstract (arXiv)

We present OneFlow, the first non-autoregressive multimodal model that enables variable-length and concurrent mixed-modal generation. Unlike autoregressive models that enforce rigid causal ordering between text and image generation, OneFlow combines an insertion-based Edit Flow for discrete text tokens with Flow Matching for image latents. OneFlow enables concurrent text-image synthesis with hierarchical sampling that prioritizes content over grammar. Through controlled experiments across model sizes from 1B to 8B, we demonstrate that OneFlow outperforms autoregressive baselines on both generation and understanding tasks while using up to 50% fewer training FLOPs. OneFlow surpasses both autoregressive and diffusion-based approaches while unlocking new capabilities for concurrent generation, iterative refinement, and natural reasoning-like generation.

Key facts. Cited by 17 papers in the map (data through 13 Oct 2026). Builds on 63 of its 69 references that are in the map. First posted on arXiv 3 Oct 2025.

Builds on

63 of 69 references.

References · 63

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,952
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,550
  3. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,376
  4. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,023
  5. 2022Flamingo: a Visual Language Model for Few-Shot Learningcited by 4,363
  6. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesiscited by 4,130
  7. 2022FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awarenesscited by 3,637
  8. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,607
  9. 2023Sigmoid Loss for Language Image Pre-Trainingcited by 3,068
  10. 2021CLIPScore: A Reference-free Evaluation Metric for Image Captioningcited by 2,407
  11. 2021Structured Denoising Diffusion Models in Discrete State-Spacescited by 1,685
  12. 2025SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Featurescited by 1,154
38 more
  1. 2022MaskGIT: Masked Generative Image Transformercited by 1,090
  2. 2023Stochastic Interpolants: A Unifying Framework for Flows and Diffusionscited by 917
  3. 2024Chameleon: Mixed-Modal Early-Fusion Foundation Modelscited by 913
  4. 2025Large Language Diffusion Modelscited by 888
  5. 2025Emerging Properties in Unified Multimodal Pretrainingcited by 872
  6. 2024Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMscited by 827
  7. 2024Simple and Effective Masked Diffusion Language Modelscited by 816
  8. 2025Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scalingcited by 799
  9. 2024Emu3: Next-Token Prediction is All You Needcited by 768
  10. 2024Autoregressive Model Beats Diffusion: Llama for Scalable Image Generationcited by 764
  11. 2024Show-o: One Single Transformer to Unify Multimodal Understanding and Generationcited by 740
  12. 2023Discrete Diffusion Modeling by Estimating the Ratios of the Data Distributioncited by 725
  13. 2024Simplified and Generalized Masked Diffusion for Discrete Datacited by 614
  14. 2024Transfusion: Predict the Next Token and Diffuse Images with One Multi-Modal Modelcited by 475
  15. 2024ELLA: Equip Diffusion Models with LLM for Enhanced Semantic Alignmentcited by 463
  16. 2024Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generationcited by 451
  17. 2023Generative Multimodal Models are In-Context Learnerscited by 446
  18. 2025Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Modelscited by 396
  19. 2024Your Absorbing Discrete Diffusion Secretly Models the Conditional Distributions of Clean Datacited by 377
  20. 2023OBELICS: An Open Web-Scale Filtered Dataset of Interleaved Image-Text Documentscited by 316
  21. 2024Discrete Flow Matchingcited by 309
  22. 2024Generative Flows on Discrete State-Spaces: Enabling Multimodal Flows with Applications to Protein Co-Designcited by 299
  23. 2024Flow Matching Guide and Codecited by 295
  24. 2025MMaDA: Multimodal Large Diffusion Language Modelscited by 244
  25. 2023Multimodal C4: An Open, Billion-scale Corpus of Images Interleaved with Textcited by 208
  26. 2024Masked Diffusion Models are Secretly Time-Agnostic Masked Models and Exploit Inaccurate Categorical Samplingcited by 206
  27. 2024MetaMorph: Multimodal Understanding and Generation via Instruction Tuningcited by 206
  28. 2025WISE: A World Knowledge-Informed Semantic Evaluation for Text-to-Image Generationcited by 199
  29. 2019Levenshtein Transformercited by 198
  30. 2024JanusFlow: Harmonizing Autoregression and Rectified Flow for Unified Multimodal Understanding and Generationcited by 162
  31. 2024Mixture-of-Transformers: A Sparse and Scalable Architecture for Multi-Modal Foundation Modelscited by 156
  32. 2019Insertion Transformer: Flexible Sequence Generation via Insertion Operationscited by 123
  33. 2024LMFusion: Adapting Pretrained Language Models for Multimodal Generationcited by 120
  34. 2025PerceptionLM: Open-Access Data and Models for Detailed Visual Understandingcited by 88
  35. 2024Generator Matching: Generative modeling with arbitrary Markov processescited by 84
  36. 2024Dual Diffusion for Unified Image Generation and Understandingcited by 76
  37. 2024Flow Matching with General Discrete Paths: A Kinetic-Optimal Perspectivecited by 56
  38. 2025Edit Flows: Flow Matching with Edit Operationscited by 53

50 most cited of 63 All 63 (JSON)

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2025: 5; 2026: 12.

17 papers.

Sort:

By area:

  1. 2026Beyond Language Modeling: An Exploration of Multimodal Pretrainingcited by 33
  2. 2026dLLM: Simple Diffusion Language Modelingcited by 14
  3. 2025From Masks to Worlds: A Hitchhiker's Guide to World Modelscited by 5
  4. 2026DFM-VLA: Iterative Action Refinement for Robot Manipulation via Discrete Flow Matchingcited by 5
  5. 2025Branching Flows: Discrete, Continuous, and Manifold Flow Matching with Splits and Deletionscited by 4
  6. 2025Loom: Diffusion-Transformer for Interleaved Generationcited by 3
  7. 2026Zatom-1: Towards a Multimodal Foundation Model for 3D Molecules and Materialscited by 3
  8. 2025Time dependent loss reweighting for flow matching and diffusion models is theoretically justifiedcited by 2
  9. 2025Flowception: Temporally Expansive Flow Matching for Video Generationcited by 2
  10. 2026Generative Molecular Morphing for Flexible-Size Design via Unbalanced Optimal Transportcited by 2
  11. 2026Towards Physics of Multimodal Pretraining: Knowledge Flow, Modality Synergy, Early Unification, and Recipescited by 2
  12. 2026TRIMS: Trajectory-Ranked Instruction Masked Supervision for Diffusion Language Modelscited by 1
5 more
  1. 2026Expanding Flow Mapscited by 1
  2. 2026PixelUMM: Encoder-Free Unified Image and Video Understanding and Generationcited by 1
  3. 2026FullFlow: Upgrading Text-to-Image Flow Matching Models for Bidirectional Vision--Language Generationcited by 0
  4. 2026HorizonFlow: Variable-Length Planning for Offline Goal-Conditioned RLcited by 0
  5. 2026Multimodal Flow: Unified Flow Modeling of Language and Vision in Embedding Spacescited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026STARFlow2: Bridging Language Models and Normalizing Flows for Unified Multimodal Generation
  2. 2026Unified Text-Image Generation with Weakness-Targeted Post-Training
  3. 2025CRAFT: Continuous Reasoning and Agentic Feedback Tuning for Multimodal Text-to-Image Generation
  4. 2024GraPE: A Generate-Plan-Edit Framework for Compositional T2I Synthesis
  5. 2025MammothModa2: A Unified AR-Diffusion Framework for Multimodal Understanding and Generation
  6. 2024ANOLE: An Open, Autoregressive, Native Large Multimodal Models for Interleaved Image-Text Generation
  7. 2026M3: High-fidelity Text-to-Image Generation via Multi-Modal, Multi-Agent and Multi-Round Visual Reasoning
  8. 2025OneIG-Bench: Omni-dimensional Nuanced Evaluation for Image Generation