Dataset Groups Activity Stream UniDiff UniDiff is a unified vision-language model that integrates discriminative and generative capabilities in vision-language tasks. BibTex: @dataset{Xiao_Dong_and_Runhui_Huang_and_Xiaoyong_Wei_and_Zequn_Jie_and_Jianxing_Yu_and_Jian_Yin_and_Xiaodan_Liang_2024, abstract = {UniDiff is a unified vision-language model that integrates discriminative and generative capabilities in vision-language tasks.}, author = {Xiao Dong and Runhui Huang and Xiaoyong Wei and Zequn Jie and Jianxing Yu and Jian Yin and Xiaodan Liang}, doi = {10.57702/5mbf8orw}, institution = {No Organization}, keyword = {'discriminative learning', 'generative learning', 'vision-language models'}, month = {dec}, publisher = {TIB}, title = {UniDiff}, url = {https://service.tib.eu/ldmservice/dataset/unidiff}, year = {2024} }
