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/Janus

Janus

Reported on 9 benchmarks across 3 tasks · 1 paper

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

Medical7 results

Image GenerationonWISE
Biology· 2024-10-17
0.28
best: 0.76 (MindOmni (w/ cot))
Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generation arXiv:2410.13848
Image GenerationonWISE
Chemistry· 2024-10-17
0.14
best: 0.58 (Bagel (w/ cot))
Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generation arXiv:2410.13848
Image GenerationonWISE
Cultural· 2024-10-17
0.16
best: 0.76 (Bagel (w/ cot))
Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generation arXiv:2410.13848
Image GenerationonWISE
Overall· 2024-10-17
0.23
best: 0.71 (MindOmni (w/ cot))
Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generation arXiv:2410.13848
Image GenerationonWISE
Physics· 2024-10-17
0.3
best: 0.75 (Bagel (w/ cot))
Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generation arXiv:2410.13848
Image GenerationonWISE
Space· 2024-10-17
0.35
best: 0.76 (MindOmni (w/ cot))
Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generation arXiv:2410.13848
Image GenerationonWISE
Time· 2024-10-17
0.26
best: 0.7 (MindOmni (w/ cot))
Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generation arXiv:2410.13848

Natural Language Processing2 results

Visual Question Answering (VQA)onMM-Vet
GPT-4 score· 2024-10-17
34.3
best: 74.24 (MMCTAgent (GPT-4 + GPT-4V))
Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generation arXiv:2410.13848
Visual Question AnsweringonMM-Vet
GPT-4 score· 2024-10-17
34.3
best: 74.24 (MMCTAgent (GPT-4 + GPT-4V))
Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generation arXiv:2410.13848