ZejunLi/MoVT-Train download history
ZejunLi/MoVT-Train is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 131 times (30 in the last 7 days), and 1,236 times in total. It ranks #93,463 among datasets by monthly downloads.
Mixture-of-Visual-Thoughts Training Data This is the training data of our paper: Mixture-of-Visual-Thoughts: Exploring Context-Adaptive Reasoning Mode Selection for General Visual Reasoning, including: SFT data for two thinking modes: text-based thinking and visually-grounded thinking (w