{"id":"2209.14156","title":"TVLT: Textless Vision-Language Transformer","url":"https://codeofpaper.com/paper/2209.14156","arxiv_url":"https://arxiv.org/abs/2209.14156","published":"2022-09-28","code":"official","best":{"full_name":"zinengtang/TVLT","url":"https://github.com/zinengtang/TVLT","tier":"official","stars":126,"license":"MIT","framework":null,"language":"Jupyter Notebook","last_commit":"2023-02-24T03:39:35"},"most_starred_community":null,"implementations":[{"full_name":"zinengtang/TVLT","url":"https://github.com/zinengtang/TVLT","tier":"official","stars":126,"license":"MIT","framework":null,"language":"Jupyter Notebook","last_commit":"2023-02-24T03:39:35"}],"possible_matches":0}