SMoLA-PaLI-X Specialist

Reported on 4 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 Processing2 results

Visual Question Answering (VQA)onInfographicVQA
ANLS· uses extra data· 2023-12-01
66.2
best: 80.3 (Gemini Ultra (pixel only))
SOTA
Omni-SMoLA: Boosting Generalist Multimodal Models with Soft Mixture of Low-rank Experts arXiv:2312.00968
Visual Question Answering (VQA)onDocVQA test
ANLS· uses extra data· 2023-12-01
0.908
best: 0.9436 (Human)
Omni-SMoLA: Boosting Generalist Multimodal Models with Soft Mixture of Low-rank Experts arXiv:2312.00968

Computer Vision2 results

Object CountingonTallyQA-Complex
Accuracy· uses extra data· 2023-12-01
77.1
SOTA
Omni-SMoLA: Boosting Generalist Multimodal Models with Soft Mixture of Low-rank Experts arXiv:2312.00968
Object CountingonTallyQA-Simple
Accuracy· uses extra data· 2023-12-01
86.3
SOTA
Omni-SMoLA: Boosting Generalist Multimodal Models with Soft Mixture of Low-rank Experts arXiv:2312.00968