mlsanityData to 14 Oct 2026

Ovis-U1 Technical Report

arXiv 2506.23044 ↗First posted 29 Jun 2025cs.CV cs.AIcited by 67

Not on the map. Why?

Abstract (arXiv)

In this report, we introduce Ovis-U1, a 3-billion-parameter unified model that integrates multimodal understanding, text-to-image generation, and image editing capabilities. Building on the foundation of the Ovis series, Ovis-U1 incorporates a diffusion-based visual decoder paired with a bidirectional token refiner, enabling image generation tasks comparable to leading models like GPT-4o. Unlike some previous models that use a frozen MLLM for generation tasks, Ovis-U1 utilizes a new unified training approach starting from a language model. Compared to training solely on understanding or generation tasks, unified training yields better performance, demonstrating the enhancement achieved by integrating these two tasks. Ovis-U1 achieves a score of 69.6 on the OpenCompass Multi-modal Academic Benchmark, surpassing recent state-of-the-art models such as Ristretto-3B and SAIL-VL-1.5-2B. In text-to-image generation, it excels with scores of 83.72 and 0.89 on the DPG-Bench and GenEval benchmarks, respectively. For image editing, it achieves 4.00 and 6.42 on the ImgEdit-Bench and GEdit-Bench-EN, respectively. As the initial version of the Ovis unified model series, Ovis-U1 pushes the boundaries of multimodal understanding, generation, and editing.

Key facts. Cited by 67 papers in the map (data through 14 Oct 2026). Builds on 58 of its 66 references that are in the map. First posted on arXiv 29 Jun 2025.

Builds on

58 of 66 references.

References · 58

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  3. 2025Qwen3 Technical Reportcited by 8,820
  4. 2025Qwen2.5-VL Technical Reportcited by 5,587
  5. 2024Qwen2.5 Technical Reportcited by 4,942
  6. 2021RoFormer: Enhanced Transformer with Rotary Position Embeddingcited by 4,703
  7. 2024Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolutioncited by 4,234
  8. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesiscited by 4,181
  9. 2022LAION-5B: An open large-scale dataset for training next generation image-text modelscited by 4,152
  10. 2022FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awarenesscited by 3,673
  11. 2022InstructPix2Pix: Learning to Follow Image Editing Instructionscited by 2,611
  12. 2023FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioningcited by 2,598
38 more
  1. 2021CLIPScore: A Reference-free Evaluation Metric for Image Captioningcited by 2,424
  2. 2023MMBench: Is Your Multi-modal Model an All-around Player?cited by 2,141
  3. 2023MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGIcited by 2,080
  4. 2025InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Modelscited by 1,834
  5. 2024HunyuanVideo: A Systematic Framework For Large Video Generative Modelscited by 1,660
  6. 2023MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contextscited by 1,614
  7. 2024Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scalingcited by 1,599
  8. 2023MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilitiescited by 1,239
  9. 2025FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Spacecited by 1,006
  10. 2023ShareGPT4V: Improving Large Multi-Modal Models with Better Captionscited by 1,005
  11. 2023GenEval: An Object-Focused Framework for Evaluating Text-to-Image Alignmentcited by 972
  12. 2024Are We on the Right Way for Evaluating Large Vision-Language Models?cited by 914
  13. 2025Emerging Properties in Unified Multimodal Pretrainingcited by 897
  14. 2025Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scalingcited by 812
  15. 2016A Diagram Is Worth A Dozen Imagescited by 804
  16. 2023MagicBrush: A Manually Annotated Dataset for Instruction-Guided Image Editingcited by 624
  17. 2023HallusionBench: An Advanced Diagnostic Suite for Entangled Language Hallucination and Visual Illusion in Large Vision-Language Modelscited by 583
  18. 2019Object Detection in 20 Years: A Surveycited by 531
  19. 2023OCRBench: On the Hidden Mystery of OCR in Large Multimodal Modelscited by 476
  20. 2024ELLA: Equip Diffusion Models with LLM for Enhanced Semantic Alignmentcited by 475
  21. 2025Step1X-Edit: A Practical Framework for General Image Editingcited by 429
  22. 2024OmniGen: Unified Image Generationcited by 394
  23. 2025BLIP3-o: A Family of Fully Open Unified Multimodal Models-Architecture, Training and Datasetcited by 376
  24. 2024OminiControl: Minimal and Universal Control for Diffusion Transformercited by 340
  25. 2024UltraEdit: Instruction-based Fine-Grained Image Editing at Scalecited by 268
  26. 2025OmniGen2: Towards Instruction-Aligned Multimodal Generationcited by 253
  27. 2024AnyEdit: Mastering Unified High-Quality Image Editing for Any Ideacited by 241
  28. 2025ImgEdit: A Unified Image Editing Dataset and Benchmarkcited by 231
  29. 2023Patch n' Pack: NaViT, a Vision Transformer for any Aspect Ratio and Resolutioncited by 229
  30. 2023JourneyDB: A Benchmark for Generative Image Understandingcited by 205
  31. 2025In-Context Edit: Enabling Instructional Image Editing with In-Context Generation in Large Scale Diffusion Transformercited by 204
  32. 2023UniControl: A Unified Diffusion Model for Controllable Visual Generation In the Wildcited by 200
  33. 2024Ovis: Structural Embedding Alignment for Multimodal Large Language Modelcited by 169
  34. 2025Less-to-More Generalization: Unlocking More Controllability by In-Context Generationcited by 154
  35. 2024OmniEdit: Building Image Editing Generalist Models Through Specialist Supervisioncited by 145
  36. 2022Wukong: A 100 Million Large-scale Chinese Cross-modal Pre-training Benchmarkcited by 114
  37. 2024Multimodal Autoregressive Pre-training of Large Vision Encoderscited by 109
  38. 2024SEED-Data-Edit Technical Report: A Hybrid Dataset for Instructional Image Editingcited by 97

50 most cited of 58 All 58 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 25; 2026: 42.

67 papers.

Sort:

By area:

  1. 2025X-Omni: Reinforcement Learning Makes Discrete Autoregressive Image Generative Models Great Againcited by 112
  2. 2025EditReward: A Human-Aligned Reward Model for Instruction-Guided Image Editingcited by 62
  3. 2025Reconstruction Alignment Improves Unified Multimodal Modelscited by 49
  4. 2025DeepMMSearch-R1: Empowering Multimodal LLMs in Multimodal Web Searchcited by 42
  5. 2025Skywork UniPic 2.0: Building Kontext Model with Online RL for Unified Multimodal Modelcited by 41
  6. 2026ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing?cited by 38
  7. 2026Beyond Language Modeling: An Exploration of Multimodal Pretrainingcited by 37
  8. 2025RealUnify: Do Unified Models Truly Benefit from Unification? A Comprehensive Benchmarkcited by 33
  9. 2026SenseNova-U1: Unifying Multimodal Understanding and Generation with NEO-unify Architecturecited by 32
  10. 2026InternVL-U: Democratizing Unified Multimodal Models for Understanding, Reasoning, Generation and Editingcited by 28
  11. 2025EditThinker: Unlocking Iterative Reasoning for Any Image Editorcited by 25
  12. 2025Factuality Matters: When Image Generation and Editing Meet Structured Visualscited by 20
38 more
  1. 2025AirCopBench: A Benchmark for Multi-drone Collaborative Embodied Perception and Reasoningcited by 20
  2. 2026Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generationcited by 18
  3. 2025ImAgent: A Unified Multimodal Agent Framework for Test-Time Scalable Image Generationcited by 17
  4. 2025GIR-Bench: Versatile Benchmark for Generating Images with Reasoningcited by 15
  5. 2025SAIL-VL2 Technical Reportcited by 14
  6. 2026RationalRewards: Reasoning Rewards Scale Visual Generation Both Training and Test Timecited by 14
  7. 2025ROVER: Benchmarking Reciprocal Cross-Modal Reasoning for Omnimodal Generationcited by 13
  8. 2026Quantifying the Gap between Understanding and Generation within Unified Multimodal Modelscited by 12
  9. 2026Lance: Unified Multimodal Modeling by Multi-Task Synergycited by 12
  10. 2025HBridge: H-Shape Bridging of Heterogeneous Experts for Unified Multimodal Understanding and Generationcited by 11
  11. 2025Does Understanding Inform Generation in Unified Multimodal Models? From Analysis to Path Forwardcited by 10
  12. 2026Mage-VL: An Efficient Codec-Native Streaming Multimodal Foundation Modelcited by 10
  13. 2025LightFusion: A Light-weighted, Double Fusion Framework for Unified Multimodal Understanding and Generationcited by 9
  14. 2025Ovis-Image Technical Reportcited by 8
  15. 2025Diffusion-SDPO: Safeguarded Direct Preference Optimization for Diffusion Modelscited by 7
  16. 2026SenseNova-U1.5: Towards Native Unified Visual Intelligencecited by 7
  17. 2025Few-Shot Synthetic Image Attribution: Identifying Unseen Generators with Limited Samplescited by 6
  18. 2025STAR: STacked AutoRegressive Scheme for Unified Multimodal Learningcited by 6
  19. 2026CoCo: Code as CoT for Text-to-Image Preview and Rare Concept Generationcited by 6
  20. 2026Boogu-Image-0.1: Boosting Open Agentic Multimodal Generation via Understanding under a Minimal Budgetcited by 6
  21. 2025FysicsWorld: A Unified Full-Modality Benchmark for Any-to-Any Understanding, Generation, and Reasoningcited by 5
  22. 2026OmniFysics: Towards Physical Intelligence Evolution via Omni-Modal Signal Processing and Network Optimizationcited by 5
  23. 2026Wan-Weaver: Interleaved Multi-modal Generation via Decoupled Trainingcited by 5
  24. 2025Are Image-to-Video Models Good Zero-Shot Image Editors?cited by 4
  25. 2026PlanViz: Evaluating Planning-Oriented Image Generation and Editing for Computer-Use Taskscited by 4
  26. 2026DuoGen: Towards General Purpose Interleaved Multimodal Generationcited by 3
  27. 2026CoCoEdit: Content-Consistent Image Editing via Region Regularized Reinforcement Learningcited by 3
  28. 2026Generative Visual Chain-of-Thought for Image Editingcited by 3
  29. 2026Mage-Flow: An Efficient Native-Resolution Foundation Model for Image Generation and Editingcited by 3
  30. 2026Towards Physics of Multimodal Pretraining: Knowledge Flow, Modality Synergy, Early Unification, and Recipescited by 3
  31. 2025UmniBench: Unified Understand and Generation Model Oriented Omni-dimensional Benchmarkcited by 2
  32. 2026UniICL: Systematizing Unified Multimodal In-context Learning through a Capability-Oriented Taxonomycited by 2
  33. 2026ViGoR-Bench: How Far Are Visual Generative Models From Zero-Shot Visual Reasoners?cited by 2
  34. 2026TRACE: High-Fidelity 3D Scene Editing via Tangible Reconstruction and Geometry-Aligned Contextual Video Maskingcited by 2
  35. 2026TorchUMM: A Unified Multimodal Model Codebase for Evaluation, Analysis, and Post-trainingcited by 2
  36. 2026InterleaveThinker: Reinforcing Agentic Interleaved Generationcited by 2
  37. 2025WeMMU: Enhanced Bridging of Vision-Language Models and Diffusion Models via Noisy Query Tokenscited by 1
  38. 2026AEGIS: Exploring the Limit of World Knowledge Capabilities for Unified Mulitmodal Modelscited by 1

50 most cited of 67 All 67 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025Ovis2.5 Technical Report
  2. 2025OpenUni: A Simple Baseline for Unified Multimodal Understanding and Generation
  3. 2024OpenING: A Comprehensive Benchmark for Judging Open-ended Interleaved Image-Text Generation
  4. 2025UniGen: Enhanced Training & Test-Time Strategies for Unified Multimodal Understanding and Generation
  5. 2024VILA-U: a Unified Foundation Model Integrating Visual Understanding and Generation
  6. 2024How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites
  7. 2025GPT-IMAGE-EDIT-1.5M: A Million-Scale, GPT-Generated Image Dataset
  8. 2026Xiaomi-OCR-0 Technical Report