TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/UniWorld-V1

UniWorld-V1

Reported on 45 benchmarks across 5 tasks · 1 paper · 6 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Medical14 results

  • Image GenerationonWISE
    Biology· 2025-06-03
    0.45
    best: 0.76 (MindOmni (w/ cot))
    UniWorld-V1: High-Resolution Semantic Encoders for Unified Visual Understanding and GenerationarXiv:2506.03147
  • Image GenerationonWISE
    Chemistry· 2025-06-03
    0.41
    best: 0.58 (Bagel (w/ cot))
    UniWorld-V1: High-Resolution Semantic Encoders for Unified Visual Understanding and GenerationarXiv:2506.03147
  • Image GenerationonWISE
    Cultural· 2025-06-03
    0.53
    best: 0.76 (Bagel (w/ cot))
    UniWorld-V1: High-Resolution Semantic Encoders for Unified Visual Understanding and GenerationarXiv:2506.03147
  • Image GenerationonWISE
    Overall· 2025-06-03
    0.55
    best: 0.71 (MindOmni (w/ cot))
    UniWorld-V1: High-Resolution Semantic Encoders for Unified Visual Understanding and GenerationarXiv:2506.03147
  • Image GenerationonWISE
    Physics· 2025-06-03
    0.59
    best: 0.75 (Bagel (w/ cot))
    UniWorld-V1: High-Resolution Semantic Encoders for Unified Visual Understanding and GenerationarXiv:2506.03147
  • Image GenerationonWISE
    Space· 2025-06-03
    0.73
    best: 0.76 (MindOmni (w/ cot))
    UniWorld-V1: High-Resolution Semantic Encoders for Unified Visual Understanding and GenerationarXiv:2506.03147
  • Image GenerationonWISE
    Time· 2025-06-03
    0.55
    best: 0.7 (MindOmni (w/ cot))
    UniWorld-V1: High-Resolution Semantic Encoders for Unified Visual Understanding and GenerationarXiv:2506.03147
  • Image GenerationonGenEval
    Color Attri.· 2025-06-03
    0.7
    best: 0.71 (UniWorld-V1 (Rewrite))
    UniWorld-V1: High-Resolution Semantic Encoders for Unified Visual Understanding and GenerationarXiv:2506.03147
  • Image GenerationonGenEval
    Colors· 2025-06-03
    0.89
    best: 0.9 (UniWorld-V1 (Rewrite))
    UniWorld-V1: High-Resolution Semantic Encoders for Unified Visual Understanding and GenerationarXiv:2506.03147
  • Image GenerationonGenEval
    Counting· 2025-06-03
    0.79
    best: 0.81 (UniWorld-V1 (Rewrite))
    UniWorld-V1: High-Resolution Semantic Encoders for Unified Visual Understanding and GenerationarXiv:2506.03147
  • Image GenerationonGenEval
    Overall· 2025-06-03
    0.8
    best: 0.95 (SD3.5-Medium+Flow-GRPO)
    UniWorld-V1: High-Resolution Semantic Encoders for Unified Visual Understanding and GenerationarXiv:2506.03147
  • Image GenerationonGenEval
    Position· 2025-06-03
    0.49
    best: 0.74 (UniWorld-V1 (Rewrite))
    UniWorld-V1: High-Resolution Semantic Encoders for Unified Visual Understanding and GenerationarXiv:2506.03147
  • Image GenerationonGenEval
    Single Obj.· 2025-06-03
    0.99
    UniWorld-V1: High-Resolution Semantic Encoders for Unified Visual Understanding and GenerationarXiv:2506.03147
  • Image GenerationonGenEval
    Two Obj.· 2025-06-03
    0.93
    best: 0.94 (MindOmni)
    UniWorld-V1: High-Resolution Semantic Encoders for Unified Visual Understanding and GenerationarXiv:2506.03147

Audio14 results

  • 10-shot image generationonGenEval
    Color Attri.· 2025-06-03
    0.7
    best: 0.71 (UniWorld-V1 (Rewrite))
    UniWorld-V1: High-Resolution Semantic Encoders for Unified Visual Understanding and GenerationarXiv:2506.03147
  • 10-shot image generationonGenEval
    Colors· 2025-06-03
    0.89
    best: 0.9 (UniWorld-V1 (Rewrite))
    UniWorld-V1: High-Resolution Semantic Encoders for Unified Visual Understanding and GenerationarXiv:2506.03147
  • 10-shot image generationonGenEval
    Counting· 2025-06-03
    0.79
    best: 0.81 (UniWorld-V1 (Rewrite))
    UniWorld-V1: High-Resolution Semantic Encoders for Unified Visual Understanding and GenerationarXiv:2506.03147
  • 10-shot image generationonGenEval
    Overall· 2025-06-03
    0.8
    best: 0.95 (SD3.5-Medium+Flow-GRPO)
    UniWorld-V1: High-Resolution Semantic Encoders for Unified Visual Understanding and GenerationarXiv:2506.03147
  • 10-shot image generationonGenEval
    Position· 2025-06-03
    0.49
    best: 0.74 (UniWorld-V1 (Rewrite))
    UniWorld-V1: High-Resolution Semantic Encoders for Unified Visual Understanding and GenerationarXiv:2506.03147
  • 10-shot image generationonGenEval
    Single Obj.· 2025-06-03
    0.99
    UniWorld-V1: High-Resolution Semantic Encoders for Unified Visual Understanding and GenerationarXiv:2506.03147
  • 10-shot image generationonGenEval
    Two Obj.· 2025-06-03
    0.93
    best: 0.94 (MindOmni)
    UniWorld-V1: High-Resolution Semantic Encoders for Unified Visual Understanding and GenerationarXiv:2506.03147
  • 1 Image, 2*2 StitchionGenEval
    Color Attri.· 2025-06-03
    0.7
    best: 0.71 (UniWorld-V1 (Rewrite))
    UniWorld-V1: High-Resolution Semantic Encoders for Unified Visual Understanding and GenerationarXiv:2506.03147
  • 1 Image, 2*2 StitchionGenEval
    Colors· 2025-06-03
    0.89
    best: 0.9 (UniWorld-V1 (Rewrite))
    UniWorld-V1: High-Resolution Semantic Encoders for Unified Visual Understanding and GenerationarXiv:2506.03147
  • 1 Image, 2*2 StitchionGenEval
    Counting· 2025-06-03
    0.79
    best: 0.81 (UniWorld-V1 (Rewrite))
    UniWorld-V1: High-Resolution Semantic Encoders for Unified Visual Understanding and GenerationarXiv:2506.03147
  • 1 Image, 2*2 StitchionGenEval
    Overall· 2025-06-03
    0.8
    best: 0.95 (SD3.5-Medium+Flow-GRPO)
    UniWorld-V1: High-Resolution Semantic Encoders for Unified Visual Understanding and GenerationarXiv:2506.03147
  • 1 Image, 2*2 StitchionGenEval
    Position· 2025-06-03
    0.49
    best: 0.74 (UniWorld-V1 (Rewrite))
    UniWorld-V1: High-Resolution Semantic Encoders for Unified Visual Understanding and GenerationarXiv:2506.03147
  • 1 Image, 2*2 StitchionGenEval
    Single Obj.· 2025-06-03
    0.99
    UniWorld-V1: High-Resolution Semantic Encoders for Unified Visual Understanding and GenerationarXiv:2506.03147
  • 1 Image, 2*2 StitchionGenEval
    Two Obj.· 2025-06-03
    0.93
    best: 0.94 (MindOmni)
    UniWorld-V1: High-Resolution Semantic Encoders for Unified Visual Understanding and GenerationarXiv:2506.03147

Computer Vision10 results

  • Image EditingonImgEdit-Data
    Adjust· 2025-06-03
    3.64
    SOTA
    UniWorld-V1: High-Resolution Semantic Encoders for Unified Visual Understanding and GenerationarXiv:2506.03147
  • Image EditingonImgEdit-Data
    Extract· 2025-06-03
    2.27
    SOTA
    UniWorld-V1: High-Resolution Semantic Encoders for Unified Visual Understanding and GenerationarXiv:2506.03147
  • Image EditingonImgEdit-Data
    Hybrid· 2025-06-03
    2.96
    SOTA
    UniWorld-V1: High-Resolution Semantic Encoders for Unified Visual Understanding and GenerationarXiv:2506.03147
  • Image EditingonImgEdit-Data
    Overall· 2025-06-03
    3.26
    best: 3.39 (BAGEL-NHR-EDIT)
    SOTA
    UniWorld-V1: High-Resolution Semantic Encoders for Unified Visual Understanding and GenerationarXiv:2506.03147
  • Image EditingonImgEdit-Data
    Remove· 2025-06-03
    3.24
    SOTA
    UniWorld-V1: High-Resolution Semantic Encoders for Unified Visual Understanding and GenerationarXiv:2506.03147
  • Image EditingonImgEdit-Data
    Replace· 2025-06-03
    3.47
    best: 3.77 (BAGEL-NHR-EDIT)
    SOTA
    UniWorld-V1: High-Resolution Semantic Encoders for Unified Visual Understanding and GenerationarXiv:2506.03147
  • Image EditingonImgEdit-Data
    Action· 2025-06-03
    2.74
    best: 4.17 (BAGEL)
    UniWorld-V1: High-Resolution Semantic Encoders for Unified Visual Understanding and GenerationarXiv:2506.03147
  • Image EditingonImgEdit-Data
    Add· 2025-06-03
    3.82
    best: 4.19 (BAGEL-NHR-EDIT)
    UniWorld-V1: High-Resolution Semantic Encoders for Unified Visual Understanding and GenerationarXiv:2506.03147
  • Image EditingonImgEdit-Data
    Background· 2025-06-03
    2.99
    best: 3.42 (BAGEL-NHR-EDIT)
    UniWorld-V1: High-Resolution Semantic Encoders for Unified Visual Understanding and GenerationarXiv:2506.03147
  • Image EditingonImgEdit-Data
    Style· 2025-06-03
    4.21
    best: 4.63 (Step1X-Edit)
    UniWorld-V1: High-Resolution Semantic Encoders for Unified Visual Understanding and GenerationarXiv:2506.03147

Natural Language Processing7 results

  • Text-to-Image GenerationonGenEval
    Color Attri.· 2025-06-03
    0.7
    best: 0.71 (UniWorld-V1 (Rewrite))
    UniWorld-V1: High-Resolution Semantic Encoders for Unified Visual Understanding and GenerationarXiv:2506.03147
  • Text-to-Image GenerationonGenEval
    Colors· 2025-06-03
    0.89
    best: 0.9 (UniWorld-V1 (Rewrite))
    UniWorld-V1: High-Resolution Semantic Encoders for Unified Visual Understanding and GenerationarXiv:2506.03147
  • Text-to-Image GenerationonGenEval
    Counting· 2025-06-03
    0.79
    best: 0.81 (UniWorld-V1 (Rewrite))
    UniWorld-V1: High-Resolution Semantic Encoders for Unified Visual Understanding and GenerationarXiv:2506.03147
  • Text-to-Image GenerationonGenEval
    Overall· 2025-06-03
    0.8
    best: 0.95 (SD3.5-Medium+Flow-GRPO)
    UniWorld-V1: High-Resolution Semantic Encoders for Unified Visual Understanding and GenerationarXiv:2506.03147
  • Text-to-Image GenerationonGenEval
    Position· 2025-06-03
    0.49
    best: 0.74 (UniWorld-V1 (Rewrite))
    UniWorld-V1: High-Resolution Semantic Encoders for Unified Visual Understanding and GenerationarXiv:2506.03147
  • Text-to-Image GenerationonGenEval
    Single Obj.· 2025-06-03
    0.99
    UniWorld-V1: High-Resolution Semantic Encoders for Unified Visual Understanding and GenerationarXiv:2506.03147
  • Text-to-Image GenerationonGenEval
    Two Obj.· 2025-06-03
    0.93
    best: 0.94 (MindOmni)
    UniWorld-V1: High-Resolution Semantic Encoders for Unified Visual Understanding and GenerationarXiv:2506.03147