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/L-Verse

L-Verse

Reported on 24 benchmarks across 5 tasks · 1 paper · 1 SOTA

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

Audio10 results

10-shot image generationonCOCO (Common Objects in Context)
FID· 2021-11-22
45.8
best: 5 (RAT-Diffusion)
L-Verse: Bidirectional Generation Between Image and Text arXiv:2111.11133
10-shot image generationonCOCO (Common Objects in Context)
FID-1· 2021-11-22
41.9
best: 19.4 (CogView)
L-Verse: Bidirectional Generation Between Image and Text arXiv:2111.11133
10-shot image generationonCOCO (Common Objects in Context)
FID-2· 2021-11-22
35.5
best: 13.9 (CogView)
L-Verse: Bidirectional Generation Between Image and Text arXiv:2111.11133
10-shot image generationonCOCO (Common Objects in Context)
FID-4· 2021-11-22
30.2
best: 15.72 (Lafite (zero-shot))
L-Verse: Bidirectional Generation Between Image and Text arXiv:2111.11133
10-shot image generationonCOCO (Common Objects in Context)
FID-8· 2021-11-22
29.83
best: 14.79 (Lafite (zero-shot))
L-Verse: Bidirectional Generation Between Image and Text arXiv:2111.11133
1 Image, 2*2 StitchionCOCO (Common Objects in Context)
FID· 2021-11-22
45.8
best: 5 (RAT-Diffusion)
L-Verse: Bidirectional Generation Between Image and Text arXiv:2111.11133
1 Image, 2*2 StitchionCOCO (Common Objects in Context)
FID-1· 2021-11-22
41.9
best: 19.4 (CogView)
L-Verse: Bidirectional Generation Between Image and Text arXiv:2111.11133
1 Image, 2*2 StitchionCOCO (Common Objects in Context)
FID-2· 2021-11-22
35.5
best: 13.9 (CogView)
L-Verse: Bidirectional Generation Between Image and Text arXiv:2111.11133
1 Image, 2*2 StitchionCOCO (Common Objects in Context)
FID-4· 2021-11-22
30.2
best: 15.72 (Lafite (zero-shot))
L-Verse: Bidirectional Generation Between Image and Text arXiv:2111.11133
1 Image, 2*2 StitchionCOCO (Common Objects in Context)
FID-8· 2021-11-22
29.83
best: 14.79 (Lafite (zero-shot))
L-Verse: Bidirectional Generation Between Image and Text arXiv:2111.11133

Natural Language Processing9 results

Image CaptioningonCOCO Captions
ROUGE-L· 2021-11-22
60.4
best: 61.1 (ExpansionNet v2 (No VL pretraining))
SOTA
L-Verse: Bidirectional Generation Between Image and Text arXiv:2111.11133
Image CaptioningonCOCO Captions
BLEU-4· 2021-11-22
39.9
best: 46.5 (mPLUG)
L-Verse: Bidirectional Generation Between Image and Text arXiv:2111.11133
Image CaptioningonCOCO Captions
METEOR· 2021-11-22
31.4
best: 33.9 (CoCa)
L-Verse: Bidirectional Generation Between Image and Text arXiv:2111.11133
Image CaptioningonCOCO Captions
SPICE· 2021-11-22
23.3
best: 27 (VAST)
L-Verse: Bidirectional Generation Between Image and Text arXiv:2111.11133
Text-to-Image GenerationonCOCO (Common Objects in Context)
FID· 2021-11-22
45.8
best: 5 (RAT-Diffusion)
L-Verse: Bidirectional Generation Between Image and Text arXiv:2111.11133
Text-to-Image GenerationonCOCO (Common Objects in Context)
FID-1· 2021-11-22
41.9
best: 19.4 (CogView)
L-Verse: Bidirectional Generation Between Image and Text arXiv:2111.11133
Text-to-Image GenerationonCOCO (Common Objects in Context)
FID-2· 2021-11-22
35.5
best: 13.9 (CogView)
L-Verse: Bidirectional Generation Between Image and Text arXiv:2111.11133
Text-to-Image GenerationonCOCO (Common Objects in Context)
FID-4· 2021-11-22
30.2
best: 15.72 (Lafite (zero-shot))
L-Verse: Bidirectional Generation Between Image and Text arXiv:2111.11133
Text-to-Image GenerationonCOCO (Common Objects in Context)
FID-8· 2021-11-22
29.83
best: 14.79 (Lafite (zero-shot))
L-Verse: Bidirectional Generation Between Image and Text arXiv:2111.11133

Medical5 results

Image GenerationonCOCO (Common Objects in Context)
FID· 2021-11-22
45.8
best: 5 (RAT-Diffusion)
L-Verse: Bidirectional Generation Between Image and Text arXiv:2111.11133
Image GenerationonCOCO (Common Objects in Context)
FID-1· 2021-11-22
41.9
best: 19.4 (CogView)
L-Verse: Bidirectional Generation Between Image and Text arXiv:2111.11133
Image GenerationonCOCO (Common Objects in Context)
FID-2· 2021-11-22
35.5
best: 13.9 (CogView)
L-Verse: Bidirectional Generation Between Image and Text arXiv:2111.11133
Image GenerationonCOCO (Common Objects in Context)
FID-4· 2021-11-22
30.2
best: 15.72 (Lafite (zero-shot))
L-Verse: Bidirectional Generation Between Image and Text arXiv:2111.11133
Image GenerationonCOCO (Common Objects in Context)
FID-8· 2021-11-22
29.83
best: 14.79 (Lafite (zero-shot))
L-Verse: Bidirectional Generation Between Image and Text arXiv:2111.11133