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/Emu3

Emu3

Reported on 18 benchmarks across 6 tasks · 1 paper · 12 SOTA

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

Audio8 results

10-shot image generationonT2I-CompBench
Color· 2024-09-27
0.7913
SOTA
Emu3: Next-Token Prediction is All You Need arXiv:2409.18869
10-shot image generationonT2I-CompBench
Shape· 2024-09-27
0.5846
SOTA
Emu3: Next-Token Prediction is All You Need arXiv:2409.18869
10-shot image generationonT2I-CompBench
Texture· 2024-09-27
0.7422
SOTA
Emu3: Next-Token Prediction is All You Need arXiv:2409.18869
1 Image, 2*2 StitchionT2I-CompBench
Color· 2024-09-27
0.7913
SOTA
Emu3: Next-Token Prediction is All You Need arXiv:2409.18869
1 Image, 2*2 StitchionT2I-CompBench
Shape· 2024-09-27
0.5846
SOTA
Emu3: Next-Token Prediction is All You Need arXiv:2409.18869
1 Image, 2*2 StitchionT2I-CompBench
Texture· 2024-09-27
0.7422
SOTA
Emu3: Next-Token Prediction is All You Need arXiv:2409.18869
10-shot image generationonGenEval
Overall· 2024-09-27
0.66
best: 0.95 (SD3.5-Medium+Flow-GRPO)
Emu3: Next-Token Prediction is All You Need arXiv:2409.18869
1 Image, 2*2 StitchionGenEval
Overall· 2024-09-27
0.66
best: 0.95 (SD3.5-Medium+Flow-GRPO)
Emu3: Next-Token Prediction is All You Need arXiv:2409.18869

Natural Language Processing6 results

Text-to-Image GenerationonT2I-CompBench
Color· 2024-09-27
0.7913
SOTA
Emu3: Next-Token Prediction is All You Need arXiv:2409.18869
Text-to-Image GenerationonT2I-CompBench
Shape· 2024-09-27
0.5846
SOTA
Emu3: Next-Token Prediction is All You Need arXiv:2409.18869
Text-to-Image GenerationonT2I-CompBench
Texture· 2024-09-27
0.7422
SOTA
Emu3: Next-Token Prediction is All You Need arXiv:2409.18869
Visual Question Answering (VQA)onMM-Vet
GPT-4 score· 2024-09-27
37.2
best: 74.24 (MMCTAgent (GPT-4 + GPT-4V))
Emu3: Next-Token Prediction is All You Need arXiv:2409.18869
Text-to-Image GenerationonGenEval
Overall· 2024-09-27
0.66
best: 0.95 (SD3.5-Medium+Flow-GRPO)
Emu3: Next-Token Prediction is All You Need arXiv:2409.18869
Visual Question AnsweringonMM-Vet
GPT-4 score· 2024-09-27
37.2
best: 74.24 (MMCTAgent (GPT-4 + GPT-4V))
Emu3: Next-Token Prediction is All You Need arXiv:2409.18869

Medical4 results

Image GenerationonT2I-CompBench
Color· 2024-09-27
0.7913
SOTA
Emu3: Next-Token Prediction is All You Need arXiv:2409.18869
Image GenerationonT2I-CompBench
Shape· 2024-09-27
0.5846
SOTA
Emu3: Next-Token Prediction is All You Need arXiv:2409.18869
Image GenerationonT2I-CompBench
Texture· 2024-09-27
0.7422
SOTA
Emu3: Next-Token Prediction is All You Need arXiv:2409.18869
Image GenerationonGenEval
Overall· 2024-09-27
0.66
best: 0.95 (SD3.5-Medium+Flow-GRPO)
Emu3: Next-Token Prediction is All You Need arXiv:2409.18869