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/PaLI-X-VPD

PaLI-X-VPD

Reported on 7 benchmarks across 3 tasks · 1 paper · 2 SOTA

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

Natural Language Processing5 results

Visual Question Answering (VQA)onOK-VQA
Accuracy· 2023-12-05
66.8
SOTA
Visual Program Distillation: Distilling Tools and Programmatic Reasoning into Vision-Language Models arXiv:2312.03052
Meme ClassificationonHateful Memes
ROC-AUC· 2023-12-05
0.892
best: 0.911 (RA-HMD (Qwen2-VL-7B))
SOTA
Visual Program Distillation: Distilling Tools and Programmatic Reasoning into Vision-Language Models arXiv:2312.03052
Visual Question Answering (VQA)onA-OKVQA
DA VQA Score· 2023-12-05
68.2
best: 70.55 (SMoLA-PaLI-X Specialist Model)
Visual Program Distillation: Distilling Tools and Programmatic Reasoning into Vision-Language Models arXiv:2312.03052
Visual Question Answering (VQA)onA-OKVQA
MC Accuracy· 2023-12-05
80.4
best: 83.75 (SMoLA-PaLI-X Specialist Model)
Visual Program Distillation: Distilling Tools and Programmatic Reasoning into Vision-Language Models arXiv:2312.03052
Visual Question Answering (VQA)onGQA test-dev
Accuracy· 2023-12-05
67.3
best: 72.1 (CFR)
Visual Program Distillation: Distilling Tools and Programmatic Reasoning into Vision-Language Models arXiv:2312.03052

Computer Vision2 results

Object CountingonTallyQA-Complex
Accuracy· 2023-12-05
76.6
best: 77.1 (SMoLA-PaLI-X Specialist)
Visual Program Distillation: Distilling Tools and Programmatic Reasoning into Vision-Language Models arXiv:2312.03052
Object CountingonTallyQA-Simple
Accuracy· 2023-12-05
86.2
best: 86.3 (SMoLA-PaLI-X Specialist)
Visual Program Distillation: Distilling Tools and Programmatic Reasoning into Vision-Language Models arXiv:2312.03052