Share your thoughts, 1 month free Claude Pro on usSee more

Few-shot Visual Question Answering on VL-ICL Bench CLEVR (test)

31.4Accuracy

MAPD

Updated 1mo ago

Evaluation Results

Method	Links
MAPD 2025.06		31.4
In-ContextPD 2025.06		30.9
LoRA ([0-15] LLM layers) 2025.06		30
Multi-TaskPD 2025.06		29.9
Model-AvgPD 2025.06		29.1
LoRA ([0-15] LLM layers + ATT) 2025.06		28.7
NoMeta-taskPD 2025.06		25.8
In-ContextPD 2025.06		24.1
NoMeta-taskPD 2025.06		18
LoRA (All LLM layers) 2025.06		15.1
Multi-TaskPD 2025.06		12.5
MAPD 2025.06		12.3
Model-AvgPD 2025.06		7.6