List your company

Audio Classification on Vocal Sound

92.4ScoreFull Model
-3.69621.25246.271.148Apr 14, 2025Jun 13, 2025Aug 13, 2025Oct 13, 2025Dec 13, 2025Feb 12, 2026Apr 14, 2026

Evaluation results

MethodLinks
Full ModelModel=VideoLLaMA2, Sparsity ratio=0%2025.0492.4100
Full ModelBackbone=VideoLLaMA2, Sparsity=0%2025.0492.4—
Full ModelBackbone=VideoLLaMA2 (7B), Sparsity Ratio=0%, Evaluation Protocol=Zero-shot2026.0492.4100
WandaModel=VideoLLaMA2, Sparsity ratio=60%2025.0492.191
ECOFLaPModel=VideoLLaMA2, Sparsity ratio=60%2025.0492.193.8
TAMPModel=VideoLLaMA2, Sparsity ratio=60%2025.0492.195
WandaBackbone=VideoLLaMA2 (7B), Sparsity Ratio=60%, Evaluation Protocol=Zero-shot2026.0492.191
ECoFLaPBackbone=VideoLLaMA2 (7B), Sparsity Ratio=60%, Evaluation Protocol=Zero-shot2026.0492.193.8
TAMPBackbone=VideoLLaMA2 (7B), Sparsity Ratio=60%, Evaluation Protocol=Zero-shot2026.0492.195
SparseGPTModel=VideoLLaMA2, Sparsity ratio=60%2025.0491.988.5
SparseGPTBackbone=VideoLLaMA2 (7B), Sparsity Ratio=60%, Evaluation Protocol=Zero-shot2026.0491.988.5
TopoVLM (Ours)Backbone=VideoLLaMA2 (7B), Sparsity Ratio=60%, Evaluation Protocol=Zero-shot2026.0491.596.7
OWLModel=VideoLLaMA2, Sparsity ratio=60%2025.0491.389.4
OWLBackbone=VideoLLaMA2 (7B), Sparsity Ratio=60%, Evaluation Protocol=Zero-shot2026.0491.389.4
LLM-StreamlineBackbone=VideoLLaMA2 (7B), Sparsity Ratio=60%, Evaluation Protocol=Zero-shot2026.0489.586.5
LLM-PrunerBackbone=VideoLLaMA2 (7B), Sparsity Ratio=60%, Evaluation Protocol=Zero-shot2026.0484.782.1
ShortGPTBackbone=VideoLLaMA2, Sparsity=25%2025.0477.9—
OWLBackbone=VideoLLaMA2, Sparsity=25%2025.0473.9—
DASBackbone=VideoLLaMA2, Sparsity=25%2025.0453.2—
ECOFLaPBackbone=VideoLLaMA2, Sparsity=25%2025.0422.9—
Shortened LLaMABackbone=VideoLLaMA2, Sparsity=25%2025.0418.3—
MagnitudeModel=VideoLLaMA2, Sparsity ratio=60%2025.04012.6
MagnitudeBackbone=VideoLLaMA2 (7B), Sparsity Ratio=60%, Evaluation Protocol=Zero-shot2026.04012.6