Look Where It Matters: High-Resolution Crops Retrieval for Efficient VLMs
Open paper
Benchmark
Model
Rank
Results
visual-question-answering-on-v-bench
AwaRes
#21
Accuracy: 71.2
visual-question-answering-vqa-on-realworldqa
AwaRes
#56
Accuracy: 68.5
chart-question-answering-on-chartqa
AwaRes
#67
1:1 Accuracy: 80.64
Rank counts only results with a code link.