List your company
ResearchFormerly WizWand

Visual Question Answering on ScienceQA (SQA^I) (test)

97AccuracyInternVL2-8B
60.0869.66579.2588.835May 22, 2024Aug 10, 2024Oct 30, 2024Jan 19, 2025Apr 10, 2025Jun 30, 2025Sep 19, 2025
Updated 8mo ago

Evaluation results

MethodLinks
InternVL2-8BModel=InternVL2-8B, Pruning Method=None, Pruning Ratio (r)=1.02025.0997
PTPModel=InternVL2-8B, Pruning Method=PTP, Pruning Ratio (r)=0.5, Balancing Weight (alpha)=0.52025.0996.7
GSearchModel=InternVL2-8B, Pruning Method=GSearch2025.0994.3
InternVL2-2BModel=InternVL2-2B, Pruning Method=None, Pruning Ratio (r)=1.02025.0994.1
PTPModel=InternVL2-2B, Pruning Method=PTP, Pruning Ratio (r)=0.5, Balancing Weight (alpha)=0.52025.0993.9
FastVModel=InternVL2-8B, Pruning Method=FastV, Pruning Ratio (r)=0.52025.0993.2
GSearchModel=InternVL2-2B, Pruning Method=GSearch2025.0992.5
PDropModel=InternVL2-8B, Pruning Method=PDrop2025.0992.1
FastVModel=InternVL2-2B, Pruning Method=FastV, Pruning Ratio (r)=0.52025.0991
Spatially-RModel=InternVL2-2B, Pruning Method=Spatially-R, Pruning Ratio (r)=0.52025.0990.4
RandomModel=InternVL2-2B, Pruning Method=Random, Pruning Ratio (r)=0.52025.0990.1
PDropModel=InternVL2-2B, Pruning Method=PDrop2025.0989.9
VTWModel=InternVL2-2B, Pruning Method=VTW2025.0975.2
Dense ConnectorResolution=336, Tokens=144, PT+IT=0.5M+0.6M, LLM=Vicuna-7B2024.0568.8
LLaVAResolution=336, Tokens=576, PT+IT=0.5M+0.6M, LLM=Vicuna-7B2024.0566.8
VTWModel=InternVL2-8B, Pruning Method=VTW2025.0962.3
Qwen-VL-ChatResolution=448, Tokens=256, PT+IT=1.4B+50M, LLM=Qwen-7B2024.0561.5