{"name":"video-prediction-policy-2","repo":"roboterax/video-prediction-policy-2","url":"https://midorreal.com/project/roboterax-video-prediction-policy-2","repository":"https://github.com/roboterax/video-prediction-policy-2","description":"Official implementation of Video Prediction Policy 2: Predict Better, Act Better","facts":{"language":{"value":"Python","source":"https://github.com/roboterax/video-prediction-policy-2","checked":"22 Nov 2026"},"homepage":{"value":"https://robert-gyj.github.io/video-prediction-policy-2/","source":"https://robert-gyj.github.io/video-prediction-policy-2/","checked":"22 Nov 2026"},"releases":{"value":"0","source":"https://github.com/roboterax/video-prediction-policy-2/releases","checked":"19 Nov 2026"},"contributors":{"value":"2","source":"https://github.com/roboterax/video-prediction-policy-2/graphs/contributors","checked":"19 Nov 2026"},"archived":{"value":"no","source":"https://github.com/roboterax/video-prediction-policy-2","checked":"22 Nov 2026"}},"stars":388.0,"writeup":{"what_it_is":"Video Prediction Policy 2 (VPP2) is a world-action model that performs video prediction and robot policy learning. It uses a three-stage pipeline: event-level video pretraining, single-step visual planning through post-training, and action learning with a mixture-of-transformers architecture.","audience":"Roboticists and researchers working on robot learning and video prediction.","claims":[{"kind":"specific","claim":"Provides zero-shot video prediction capability","excerpt":"strong zero-shot generalization in both video prediction and action generation","status":"not_checked"},{"kind":"specific","claim":"Includes Stage-1 video model that generates 49 frames","excerpt":"Stage-1 (49 frames)","status":"not_checked"},{"kind":"specific","claim":"Includes Stage-2 video model that generates 17 frames","excerpt":"Stage-2 (17 frames)","status":"not_checked"}],"alternatives":[],"written_by":"AI, from the project's README","date":"2026-10-14"},"why_now":null,"owner_supplied":null,"score":{"verdict":"mid","hype":25,"reality":24,"gap":1,"momentum":0.4,"confidence":60,"version":"score-2.0","rule":"verdict-2.0","calculated_at":"2026-11-22T08:00:00+00:00","verdict_source":"rule"},"early_read":null,"changes":[{"date":"2026-10-08T06:58:48+00:00","text":"Repository created","source":"https://github.com/roboterax/video-prediction-policy-2"}],"cite":"video-prediction-policy-2 is a GitHub project at https://github.com/roboterax/video-prediction-policy-2 written mainly in Python, described there as \"Official implementation of Video Prediction Policy 2: Predict Better, Act Better\".","attribution":"Data from Mid or Real, https://midorreal.com/project/roboterax-video-prediction-policy-2, checked 22 November 2026. Attribution with a link is required.","still_real":null}