zwyang6/Perception_ZwZ-RL-VQA download history
zwyang6/Perception_ZwZ-RL-VQA is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 555 times (10 in the last 7 days), and 1,329 times in total. It ranks #30,514 among datasets by monthly downloads.
ZwZ-RL-VQA: Region-to-Image Distilled Training Data for Fine-Grained Perception This dataset contains 74K high-quality VQA pairs generated via Region-to-Image Distillation (R2I) for training multimodal large language models (MLLMs) on fine-grained perception tasks without test-time tool u