{"id":"2210.03347","title":"Pix2Struct: Screenshot Parsing as Pretraining for Visual Language Understanding","url":"https://codeofpaper.com/paper/2210.03347","arxiv_url":"https://arxiv.org/abs/2210.03347","published":"2022-10-07","code":"official","best":{"full_name":"google-research/pix2struct","url":"https://github.com/google-research/pix2struct","tier":"official","stars":693,"license":"Apache-2.0","framework":null,"language":"Python","last_commit":"2026-10-05T14:37:56"},"most_starred_community":null,"implementations":[{"full_name":"google-research/pix2struct","url":"https://github.com/google-research/pix2struct","tier":"official","stars":693,"license":"Apache-2.0","framework":null,"language":"Python","last_commit":"2026-10-05T14:37:56"}],"possible_matches":0}