Reason Through the Latent! Making Latent Visual Reasoning Necessary
Open paper
Benchmark
Model
Rank
Results
visual-question-answering-vqa-on-mmvp
CVRR (Qwen2.5-VL-7B)
#3
Paired Accuracy: 52.7
visual-question-answering-on-v-bench
CVRR (Qwen2.5-VL-7B)
#14
Accuracy: 81.2
Rank counts only results with a code link.