SMoLA-PaLI-X Specialist Model

Reported on 5 benchmarks across 2 tasks · 1 paper · 3 SOTA

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

Natural Language Processing4 results

Visual Question Answering (VQA)onAI2D
EM· uses extra data· 2023-12-01
82.5
SOTA
Omni-SMoLA: Boosting Generalist Multimodal Models with Soft Mixture of Low-rank Experts arXiv:2312.00968
Visual Question Answering (VQA)onA-OKVQA
DA VQA Score· uses extra data· 2023-12-01
70.55
SOTA
Omni-SMoLA: Boosting Generalist Multimodal Models with Soft Mixture of Low-rank Experts arXiv:2312.00968
Visual Question Answering (VQA)onA-OKVQA
MC Accuracy· uses extra data· 2023-12-01
83.75
SOTA
Omni-SMoLA: Boosting Generalist Multimodal Models with Soft Mixture of Low-rank Experts arXiv:2312.00968
Visual Question Answering (VQA)onChartQA
1:1 Accuracy· uses extra data· 2023-12-01
74.6
best: 81.3 (ChartPaLI-5B + PaLM 2-S)
Omni-SMoLA: Boosting Generalist Multimodal Models with Soft Mixture of Low-rank Experts arXiv:2312.00968

Computer Code1 result

Chart Question AnsweringonChartQA
1:1 Accuracy· uses extra data· 2023-12-01
74.6
best: 81.3 (ChartPaLI-5B + PaLM 2-S)
Omni-SMoLA: Boosting Generalist Multimodal Models with Soft Mixture of Low-rank Experts arXiv:2312.00968