bytedance-research/KIE-HVQA download history
bytedance-research/KIE-HVQA is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 748 times (122 in the last 7 days), and 5,152 times in total. It ranks #24,149 among datasets by monthly downloads.
KIE-HVQA Seeing is Believing? Mitigating OCR Hallucinations in Multimodal Large Language Models Data for the paper Seeing is Believing? Mitigating OCR Hallucinations in Multimodal Large Language Models What's New [2025/09/19] The paper has been accepted by NeurIPS