jankin123/OmniVideo-R1 download history
jankin123/OmniVideo-R1 is a video text to text dataset on the Hugging Face Hub. In the last 30 days it was downloaded 77 times (21 in the last 7 days), and 752 times in total. It ranks #136,979 among datasets by monthly downloads.
OmniVideo-R1 Training Data Training data for OmniVideo-R1: Reinforcing Audio-visual Reasoning with Query Intention and Modality Attention. Dataset Description This dataset contains the preprocessed training data used in the OmniVideo-R1 framework, which improves mixed-mod