Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

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

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

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

Models/Infinity-2B

Infinity-2B

Reported on 15 benchmarks across 1 task · 1 paper · 8 SOTA

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

Medical15 results

Image GenerationonTextAtlasEval
StyledTextSynth OCR (Accuracy)· 2024-10-24
0.8
best: 30.58 (Dalle3)
SOTA
Infinity-MM: Scaling Multimodal Performance with Large-Scale and High-Quality Instruction Data arXiv:2410.18558
Image GenerationonTextAtlasEval
TextScenesHQ FID· 2024-10-24
71.59
best: 64.44 (SD3.5 Large)
SOTA
Infinity-MM: Scaling Multimodal Performance with Large-Scale and High-Quality Instruction Data arXiv:2410.18558
Image GenerationonTextAtlasEval
TextScenesHQ OCR (Accuracy)· 2024-10-24
1.06
best: 69.26 (Dalle3)
SOTA
Infinity-MM: Scaling Multimodal Performance with Large-Scale and High-Quality Instruction Data arXiv:2410.18558
Image GenerationonTextAtlasEval
TextScenesHQ OCR (Cer)· 2024-10-24
0.88
best: 0.57 (Grok3)
SOTA
Infinity-MM: Scaling Multimodal Performance with Large-Scale and High-Quality Instruction Data arXiv:2410.18558
Image GenerationonTextAtlasEval
TextScenesHQ OCR (F1 Score)· 2024-10-24
1.74
best: 51.63 (Dalle3)
SOTA
Infinity-MM: Scaling Multimodal Performance with Large-Scale and High-Quality Instruction Data arXiv:2410.18558
Image GenerationonTextAtlasEval
TextVisionBlend Clip Score· 2024-10-24
0.1979
SOTA
Infinity-MM: Scaling Multimodal Performance with Large-Scale and High-Quality Instruction Data arXiv:2410.18558
Image GenerationonTextAtlasEval
TextVisionBlend OCR (Accuracy)· 2024-10-24
2.98
best: 41.54 (Grok3)
SOTA
Infinity-MM: Scaling Multimodal Performance with Large-Scale and High-Quality Instruction Data arXiv:2410.18558
Image GenerationonTextAtlasEval
TextVsionBlend OCR (F1 Score)· 2024-10-24
3.44
best: 44.22 (Grok3)
SOTA
Infinity-MM: Scaling Multimodal Performance with Large-Scale and High-Quality Instruction Data arXiv:2410.18558
Image GenerationonTextAtlasEval
StyledTextSynth Clip Score· 2024-10-24
0.2727
best: 0.2938 (Grok3)
Infinity-MM: Scaling Multimodal Performance with Large-Scale and High-Quality Instruction Data arXiv:2410.18558
Image GenerationonTextAtlasEval
StyledTextSynth FID· 2024-10-24
84.95
best: 71.09 (SD3.5 Large)
Infinity-MM: Scaling Multimodal Performance with Large-Scale and High-Quality Instruction Data arXiv:2410.18558
Image GenerationonTextAtlasEval
StyledTextSynth OCR (Cer)· 2024-10-24
0.93
best: 0.73 (Grok3)
Infinity-MM: Scaling Multimodal Performance with Large-Scale and High-Quality Instruction Data arXiv:2410.18558
Image GenerationonTextAtlasEval
StyledTextSynth OCR (F1 Score)· 2024-10-24
1.42
best: 38.25 (Dalle3)
Infinity-MM: Scaling Multimodal Performance with Large-Scale and High-Quality Instruction Data arXiv:2410.18558
Image GenerationonTextAtlasEval
TextScenesHQ Clip Score· 2024-10-24
0.2346
best: 0.3367 (Dalle3)
Infinity-MM: Scaling Multimodal Performance with Large-Scale and High-Quality Instruction Data arXiv:2410.18558
Image GenerationonTextAtlasEval
TextVisionBlend FID· 2024-10-24
95.69
best: 81.29 (PixArt-Sigma)
Infinity-MM: Scaling Multimodal Performance with Large-Scale and High-Quality Instruction Data arXiv:2410.18558
Image GenerationonTextAtlasEval
TextVisionBlend OCR (Cer)· 2024-10-24
0.83
best: 0.57 (Grok3)
Infinity-MM: Scaling Multimodal Performance with Large-Scale and High-Quality Instruction Data arXiv:2410.18558