LL3DA

Reported on 4 benchmarks across 1 task · 1 paper · 4 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)onScanQA Test w/ objects
BLEU-4· 2023-04-17
13.5
best: 24.06 (BridgeQA)
SOTA
Visual Instruction Tuning arXiv:2304.08485
Visual Question Answering (VQA)onScanQA Test w/ objects
CIDEr· 2023-04-17
76.8
best: 103.1 (LLaVA-3D)
SOTA
Visual Instruction Tuning arXiv:2304.08485
Visual Question Answering (VQA)onScanQA Test w/ objects
METEOR· 2023-04-17
15.9
best: 20.8 (LLaVA-3D)
SOTA
Visual Instruction Tuning arXiv:2304.08485
Visual Question Answering (VQA)onScanQA Test w/ objects
ROUGE· 2023-04-17
37.3
best: 49.6 (LLaVA-3D)
SOTA
Visual Instruction Tuning arXiv:2304.08485