mlsanityData to 14 Oct 2026

Show-o2: Improved Native Unified Multimodal Models

arXiv 2506.15564 ↗First posted 18 Jun 2025cs.CVcited by 250

On the map: Diffusion models → Image generation, text-to-image and editing

Abstract (arXiv)

This paper presents improved native unified multimodal models, i.e., Show-o2, that leverage autoregressive modeling and flow matching. Built upon a 3D causal variational autoencoder space, unified visual representations are constructed through a dual-path of spatial (-temporal) fusion, enabling scalability across image and video modalities while ensuring effective multimodal understanding and generation. Based on a language model, autoregressive modeling and flow matching are natively applied to the language head and flow head, respectively, to facilitate text token prediction and image/video generation. A two-stage training recipe is designed to effectively learn and scale to larger models. The resulting Show-o2 models demonstrate versatility in handling a wide range of multimodal understanding and generation tasks across diverse modalities, including text, images, and videos. Code and models are released at https://github.com/showlab/Show-o.

Key facts. Cited by 250 papers in the map (data through 14 Oct 2026). Placed in Image generation, text-to-image and editing, one of 14 directions in Diffusion models. Builds on 116 of its 135 references that are in the map. First posted on arXiv 18 Jun 2025.

Builds on

116 of 135 references.

Closest ancestors · 14

Same direction, newest first

  1. 2025Muddit: Liberating Generation Beyond Text-to-Image with a Unified Discrete Diffusion Model29 May
  2. 2025FUDOKI: Discrete Flow-based Unified Understanding and Generation via Kinetic-Optimal Velocities26 May
  3. 2025LaViDa: A Large Diffusion Language Model for Multimodal Understanding22 May
  4. 2025MMaDA: Multimodal Large Diffusion Language Models21 May
  5. 2025BLIP3-o: A Family of Fully Open Unified Multimodal Models-Architecture, Training and Dataset14 May
  6. 2025Unified Multimodal Discrete Diffusion26 Mar
  7. 2024Dual Diffusion for Unified Image Generation and Understanding31 Dec
  8. 2024Emu3: Next-Token Prediction is All You Need27 Sep
  9. 2024VILA-U: a Unified Foundation Model Integrating Visual Understanding and Generation6 Sep
  10. 2024Hunyuan-DiT: A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding14 May
  11. 2024ELLA: Equip Diffusion Models with LLM for Enhanced Semantic Alignment8 Mar
  12. 2024Playground v2.5: Three Insights towards Enhancing Aesthetic Quality in Text-to-Image Generation27 Feb
2 more
  1. 2023GenEval: An Object-Focused Framework for Evaluating Text-to-Image Alignment17 Oct
  2. 2023BoxDiff: Text-to-Image Synthesis with Training-Free Box-Constrained Diffusion20 Jul

Other references · 102

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  3. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  4. 2023Visual Instruction Tuningcited by 7,869
  5. 2022Scalable Diffusion Models with Transformerscited by 6,054
  6. 2022Flow Matching for Generative Modelingcited by 5,702
  7. 2025Qwen2.5-VL Technical Reportcited by 5,587
  8. 2024Qwen2.5 Technical Reportcited by 4,942
  9. 2023Improved Baselines with Visual Instruction Tuningcited by 4,418
  10. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesiscited by 4,181
  11. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,700
  12. 2024LLaVA-OneVision: Easy Visual Task Transfercited by 2,719
38 more
  1. 2025Wan: Open and Advanced Large-Scale Video Generative Modelscited by 2,708
  2. 2023Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasetscited by 2,581
  3. 2024CogVideoX: Text-to-Video Diffusion Models with An Expert Transformercited by 2,261
  4. 2023Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyondcited by 2,224
  5. 2023MMBench: Is Your Multi-modal Model an All-around Player?cited by 2,141
  6. 2023MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGIcited by 2,080
  7. 2023VBench: Comprehensive Benchmark Suite for Video Generative Modelscited by 1,822
  8. 2023MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Modelscited by 1,652
  9. 2024Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scalingcited by 1,599
  10. 2019Root Mean Square Layer Normalizationcited by 1,480
  11. 2023AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuningcited by 1,433
  12. 2021Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Conceptscited by 1,216
  13. 2021Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrievalcited by 1,177
  14. 2023ShareGPT4V: Improving Large Multi-Modal Models with Better Captionscited by 1,005
  15. 2022Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generationcited by 961
  16. 2023SEED-Bench: Benchmarking Multimodal LLMs with Generative Comprehensioncited by 940
  17. 2024Chameleon: Mixed-Modal Early-Fusion Foundation Modelscited by 927
  18. 2024Are We on the Right Way for Evaluating Large Vision-Language Models?cited by 914
  19. 2025Emerging Properties in Unified Multimodal Pretrainingcited by 897
  20. 2023PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesiscited by 864
  21. 2025Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scalingcited by 812
  22. 2016A Diagram Is Worth A Dozen Imagescited by 804
  23. 2024Autoregressive Model Beats Diffusion: Llama for Scalable Image Generationcited by 777
  24. 2024Show-o: One Single Transformer to Unify Multimodal Understanding and Generationcited by 752
  25. 2023VILA: On Pre-training for Visual Language Modelscited by 692
  26. 2023ModelScope Text-to-Video Technical Reportcited by 658
  27. 2024Autoregressive Image Generation without Vector Quantizationcited by 651
  28. 2023NExT-GPT: Any-to-Any Multimodal LLMcited by 615
  29. 2023VideoCrafter1: Open Diffusion Models for High-Quality Video Generationcited by 535
  30. 2024Long Context Transfer from Language to Visioncited by 515
  31. 2022All are Worth Words: A ViT Backbone for Diffusion Modelscited by 502
  32. 2023VideoPoet: A Large Language Model for Zero-Shot Video Generationcited by 492
  33. 2024Transfusion: Predict the Next Token and Diffuse Images with One Multi-Modal Modelcited by 483
  34. 2023DynamiCrafter: Animating Open-domain Images with Video Diffusion Priorscited by 471
  35. 2024Panda-70M: Captioning 70M Videos with Multiple Cross-Modality Teacherscited by 393
  36. 2023I2VGen-XL: High-Quality Image-to-Video Synthesis via Cascaded Diffusion Modelscited by 350
  37. 2024OpenVid-1M: A Large-Scale High-Quality Dataset for Text-to-video Generationcited by 341
  38. 2024SEED-X: Multimodal Models with Unified Multi-granularity Comprehension and Generationcited by 331

50 most cited of 102 All 102 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 80; 2026: 170.

250 papers.

Sort:

By area:

  1. 2025Qwen-Image Technical Reportcited by 1,044
  2. 2025Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformercited by 277
  3. 2025Motus: A Unified Latent Action World Modelcited by 251
  4. 2025Thinking with Images for Multimodal Reasoning: Foundations, Methods, and Future Frontierscited by 199
  5. 2025X-Omni: Reinforcement Learning Makes Discrete Autoregressive Image Generative Models Great Againcited by 112
  6. 2025Latent Visual Reasoningcited by 104
  7. 2025Pref-GRPO: Pairwise Preference Reward-based GRPO for Stable Text-to-Image Reinforcement Learningcited by 92
  8. 2025UniVideo: Unified Understanding, Generation, and Editing for Videoscited by 87
  9. 2025NextStep-1: Toward Autoregressive Image Generation with Continuous Tokens at Scalecited by 57
  10. 2025OneCAT: Decoder-Only Auto-Regressive Model for Unified Understanding and Generationcited by 50
  11. 2025Reconstruction Alignment Improves Unified Multimodal Modelscited by 49
  12. 2025UniLiP: Adapting CLIP for Unified Multimodal Understanding, Generation and Editingcited by 44
38 more
  1. 2025G2VLM: Geometry Grounded Vision Language Model with Unified 3D Reconstruction and Spatial Reasoningcited by 44
  2. 2025Interleaving Reasoning for Better Text-to-Image Generationcited by 41
  3. 2025Omni-Video: Democratizing Unified Video Understanding and Generationcited by 40
  4. 2025FLUX-Reason-6M & PRISM-Bench: A Million-Scale Text-to-Image Reasoning Dataset and Comprehensive Benchmarkcited by 38
  5. 2026Beyond Language Modeling: An Exploration of Multimodal Pretrainingcited by 37
  6. 2026LongCat-Next: Lexicalizing Modalities as Discrete Tokenscited by 36
  7. 2025Easier Painting Than Thinking: Can Text-to-Image Models Set the Stage, but Not Direct the Play?cited by 34
  8. 2025TUNA: Taming Unified Visual Representations for Native Unified Multimodal Modelscited by 34
  9. 2025RealUnify: Do Unified Models Truly Benefit from Unification? A Comprehensive Benchmarkcited by 33
  10. 2026SenseNova-U1: Unifying Multimodal Understanding and Generation with NEO-unify Architecturecited by 32
  11. 2025EO-1: An Open Unified Embodied Foundation Model for General Robot Controlcited by 31
  12. 2025JarvisEvo: Towards a Self-Evolving Photo Editing Agent with Synergistic Editor-Evaluator Optimizationcited by 31
  13. 2025AToken: A Unified Tokenizer for Visioncited by 30
  14. 2026BagelVLA: Enhancing Long-Horizon Manipulation via Interleaved Vision-Language-Action Generationcited by 30
  15. 2025Ming-UniVision: Joint Image Understanding and Generation with a Unified Continuous Tokenizercited by 28
  16. 2026InternVL-U: Democratizing Unified Multimodal Models for Understanding, Reasoning, Generation and Editingcited by 28
  17. 2026VINO: A Unified Visual Generator with Interleaved OmniModal Contextcited by 26
  18. 2025UniGenBench++: A Unified Semantic Evaluation Benchmark for Text-to-Image Generationcited by 25
  19. 2025UniFlow: A Unified Pixel Flow Tokenizer for Visual Understanding and Generationcited by 23
  20. 2025Lumos-1: On Autoregressive Video Generation with Discrete Diffusion from a Unified Model Perspectivecited by 22
  21. 2025GenExam: A Multidisciplinary Text-to-Image Examcited by 22
  22. 2025SRUM: Fine-Grained Self-Rewarding for Unified Multimodal Modelscited by 22
  23. 2025Reasoning via Video: The First Evaluation of Video Models' Reasoning Abilities through Maze-Solving Taskscited by 22
  24. 2025Thinking with Camera: A Unified Multimodal Model for Camera-Centric Understanding and Generationcited by 19
  25. 2025Mull-Tokens: Modality-Agnostic Latent Thinkingcited by 19
  26. 2025Uni-X: Mitigating Modality Conflict with a Two-End-Separated Architecture for Unified Multimodal Modelscited by 18
  27. 2025Thinking-while-Generating: Interleaving Textual Reasoning throughout Visual Generationcited by 18
  28. 2026Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generationcited by 18
  29. 2025Generative Universal Verifier as Multimodal Meta-Reasonercited by 17
  30. 2025Omni-View: Unlocking How Generation Facilitates Understanding in Unified 3D Model based on Multiview imagescited by 17
  31. 2025TwinFlow: Realizing One-step Generation on Large Models with Self-adversarial Flowscited by 17
  32. 2025Query-Kontext: An Unified Multimodal Model for Image Generation and Editingcited by 15
  33. 2025GIR-Bench: Versatile Benchmark for Generating Images with Reasoningcited by 15
  34. 2025UniVA: Universal Video Agent towards Open-Source Next-Generation Video Generalistcited by 15
  35. 2025Vidarc: Embodied Video Diffusion Model for Closed-loop Controlcited by 15
  36. 2026NextFlow: Unified Sequential Modeling Activates Multimodal Understanding and Generationcited by 14
  37. 2026DeepGen 1.0: A Lightweight Unified Multimodal Model for Advancing Image Generation and Editingcited by 14
  38. 2025Unified Multimodal Models as Auto-Encoderscited by 13

50 most cited of 250 All 250 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025MANZANO: A Simple and Scalable Unified Multimodal Model with a Hybrid Vision Tokenizer
  2. 2025ARMOR: Empowering Multimodal Understanding Model with Interleaved Multimodal Generation Capability
  3. 2026UVU: Improving Multimodal Understanding via Vision-Language Unified Autoregressive Paradigm
  4. 2025Vision as a Dialect: Unifying Visual Understanding and Generation via Text-Aligned Representations
  5. 2025Autoregressive Semantic Visual Reconstruction Helps VLMs Understand Better
  6. 2026More Than Seeing: Vision as Scalable Anchors in Native Multimodal Pre-Training
  7. 2026Intern Lumina U2: A Multi-Codebook Diffusion Large Language Model for Omni-Visual Understanding and Image Generation
  8. 2025Generative Multimodal Pretraining with Discrete Diffusion Timestep Tokens