{"id":"2605.28132","title":"Which Pretraining Paradigm Better Serves Spatial Intelligence? An Empirical Comparison of Vision-Language and Video Generation Models","url":"https://codeofpaper.com/paper/2605.28132","arxiv_url":"https://arxiv.org/abs/2605.28132","published":"2026-05-27","code":"official","best":{"full_name":"om-ai-lab/Probing-VLM-VGM","url":"https://github.com/om-ai-lab/Probing-VLM-VGM","tier":"official","stars":15,"license":null,"framework":null,"language":"Python","last_commit":"2026-05-28T18:19:32"},"most_starred_community":null,"implementations":[{"full_name":"om-ai-lab/Probing-VLM-VGM","url":"https://github.com/om-ai-lab/Probing-VLM-VGM","tier":"official","stars":15,"license":null,"framework":null,"language":"Python","last_commit":"2026-05-28T18:19:32"}],"possible_matches":4}