Loading...
Loading...
Available on 1 platform
Sign in to view source links and access this dataset
Vision-OPD-6K is a training dataset for the Vision-OPD framework, which learns to see fine details for multimodal large language models. The dataset was created by author yuanqianhao and was last updated on the Hugging Face platform in May 2026. It supports a self-distillation method that transfers a model's regional perception to its full-image policy without external labels or tools.
License is unknown; users must verify permissions before use.