List your company

Audiovisual Question Answering on MUSIC-QA

100Relative (%)Full Model
9.10432.70256.379.898Apr 14, 2025Jun 13, 2025Aug 13, 2025Oct 13, 2025Dec 13, 2025Feb 12, 2026Apr 14, 2026

Evaluation results

MethodLinks
Full ModelModel=VideoLLaMA2, Sparsity ratio=0%2025.0410079.4—
Full ModelBackbone=VideoLLaMA2 (7B), Sparsity Ratio=0%, Evaluation Protocol=Zero-shot2026.04100—79.4
TopoVLM (Ours)Backbone=VideoLLaMA2 (7B), Sparsity Ratio=60%, Evaluation Protocol=Zero-shot2026.0496.7—72.5
TAMPModel=VideoLLaMA2, Sparsity ratio=60%2025.049572.6—
TAMPBackbone=VideoLLaMA2 (7B), Sparsity Ratio=60%, Evaluation Protocol=Zero-shot2026.0495—72.6
ECOFLaPModel=VideoLLaMA2, Sparsity ratio=60%2025.0493.873—
ECoFLaPBackbone=VideoLLaMA2 (7B), Sparsity Ratio=60%, Evaluation Protocol=Zero-shot2026.0493.8—73
WandaModel=VideoLLaMA2, Sparsity ratio=60%2025.049173.3—
WandaBackbone=VideoLLaMA2 (7B), Sparsity Ratio=60%, Evaluation Protocol=Zero-shot2026.0491—73.3
OWLModel=VideoLLaMA2, Sparsity ratio=60%2025.0489.468.9—
OWLBackbone=VideoLLaMA2 (7B), Sparsity Ratio=60%, Evaluation Protocol=Zero-shot2026.0489.4—68.9
SparseGPTModel=VideoLLaMA2, Sparsity ratio=60%2025.0488.570.6—
SparseGPTBackbone=VideoLLaMA2 (7B), Sparsity Ratio=60%, Evaluation Protocol=Zero-shot2026.0488.5—70.6
LLM-StreamlineBackbone=VideoLLaMA2 (7B), Sparsity Ratio=60%, Evaluation Protocol=Zero-shot2026.0486.5—71.8
LLM-PrunerBackbone=VideoLLaMA2 (7B), Sparsity Ratio=60%, Evaluation Protocol=Zero-shot2026.0482.1—66.2
MagnitudeModel=VideoLLaMA2, Sparsity ratio=60%2025.0412.60—
MagnitudeBackbone=VideoLLaMA2 (7B), Sparsity Ratio=60%, Evaluation Protocol=Zero-shot2026.0412.6—0
DASBackbone=VideoLLaMA2, Sparsity=25%2025.04——45.8
ECOFLaPBackbone=VideoLLaMA2, Sparsity=25%2025.04——26.8
Full ModelBackbone=VideoLLaMA2, Sparsity=0%2025.04——79.4
OWLBackbone=VideoLLaMA2, Sparsity=25%2025.04——36.8
Shortened LLaMABackbone=VideoLLaMA2, Sparsity=25%2025.04——25.7
ShortGPTBackbone=VideoLLaMA2, Sparsity=25%2025.04——44.8