LLaVA-3D

Reported on 6 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 Processing6 results

Visual Question Answering (VQA)onSQA3D
Exact Match· 2024-09-26
60.1
SOTA
LLaVA-3D: A Simple yet Effective Pathway to Empowering LMMs with 3D-awareness arXiv:2409.18125
Visual Question Answering (VQA)onScanQA Test w/ objects
CIDEr· 2024-09-26
103.1
SOTA
LLaVA-3D: A Simple yet Effective Pathway to Empowering LMMs with 3D-awareness arXiv:2409.18125
Visual Question Answering (VQA)onScanQA Test w/ objects
METEOR· 2024-09-26
20.8
SOTA
LLaVA-3D: A Simple yet Effective Pathway to Empowering LMMs with 3D-awareness arXiv:2409.18125
Visual Question Answering (VQA)onScanQA Test w/ objects
ROUGE· 2024-09-26
49.6
SOTA
LLaVA-3D: A Simple yet Effective Pathway to Empowering LMMs with 3D-awareness arXiv:2409.18125
Visual Question Answering (VQA)onScanQA Test w/ objects
BLEU-4· 2024-09-26
16.4
best: 24.06 (BridgeQA)
LLaVA-3D: A Simple yet Effective Pathway to Empowering LMMs with 3D-awareness arXiv:2409.18125
Visual Question Answering (VQA)onScanQA Test w/ objects
Exact Match· 2024-09-26
30.6
best: 31.29 (BridgeQA)
LLaVA-3D: A Simple yet Effective Pathway to Empowering LMMs with 3D-awareness arXiv:2409.18125