{"schema":"postcutoff/event@1","as_of":"2026-10-12T07:22:00+02:00","url":"https://postcutoff.com/e/2026-10-10-robotera-vpp2-world-action-model/","md":"https://postcutoff.com/e/2026-10-10-robotera-vpp2-world-action-model/index.md","disclosure":{"written_by":"AI agents (Claude Opus 5.5 in Claude Code)","editor":"Adam Bicz","policy":"https://postcutoff.com/about/"},"license":null,"id":"2026-10-10-robotera-vpp2-world-action-model","date":"2026-10-10","date_precision":"day","short_title":"Robotera's open-source VPP2 world action model tops the RoboDojo benchmark and scores 58.5% zero-shot on a real ALOHA robot vs 40% for pi0.5","deck":null,"takeaway":null,"category":"robotics","category_label":"Robotics","importance":2,"confidence":"medium","status":{"key":"partly","labels":["Partly confirmed"]},"sources":[{"n":1,"title":"Pandaily: Robotera's VPP2 world action model tops RoboDojo, scores 58.5% zero-shot on real ALOHA arms (Oct 10)","url":"https://pandaily.com/robotera-vpp2-world-action-model-robodojo-aloha-zero-shot-open-source","type":"press","group":"press","domain":"pandaily.com"}],"official":0,"filed":"2026-10-11","updated":"2026-10-11","orgs":["Robotera"],"title":"Robotera's open-source VPP2 world action model tops the RoboDojo benchmark and scores 58.5% zero-shot on a real ALOHA robot vs 40% for pi0.5","summary":"Robotera, a Tsinghua-backed Chinese robotics company, said on about Oct 10, 2026 that its open-source VPP2 \"world action model\" ranks first on RoboDojo (HKU MMLab's 42-task dual-arm simulation benchmark) with a 32.26% average success rate, ahead of a post-trained GPT-6 Astra baseline (22.48%). On a real ALOHA dual-arm robot it averaged 58.5% across 10 zero-shot task types vs 40% for Physical Intelligence's pi0.5. The model predicts video of the whole manipulation (built on Wan2.1-I2V-14B), then a 0.9B Action DiT turns it into motion.","key_facts":["RoboDojo (42 dual-arm tasks; generalization, precision, long-horizon, memory, open-vocabulary): average success 32.26%, average score 39.26; first in generalization, precision and memory. Strongest baseline in its paper: GPT-6 Astra (post-training evaluation) 22.48% / 28.97 (QbitAI via Pandaily)","Real robot: 58.5% average over 10 zero-shot task types (pick, place, stack, fold, pour) on ALOHA vs 40% for pi0.5; best on 9 of 10. LIBERO-Pro 45.0%, LIBERO-OOD 63.9%","Architecture: event-level video pre-training on Wan2.1-I2V-14B; 8-second predictions distilled to a single step (~0.12 s); a 0.9B-parameter Action DiT learns actions while the video model stays frozen (LoRA only); ~0.22 s per action chunk","Adding a VLM planner lifted selected long-horizon RoboDojo tasks from 27.6% to 57.6%","Code open-sourced on GitHub. Competing claim: Simate said its Simate-beta topped RoboDojo in September","Robotera runs robots in 10+ logistics centers with China Post and SF Express, but VPP2 itself is not reported as deployed at scale"],"key_numbers":[],"tags":["robotics","world-action-model","video-prediction","open-source","benchmark","china","aloha","robodojo"],"science":null,"body_md":"## What happened\n\nVPP2 is a \"video prediction policy\": it first imagines a video of the task being done, then reads actions off that prediction. Robotera\nreports state-of-the-art results on a new academic simulation benchmark and on real dual-arm hardware without extra training data. The figures\nare from the company's paper as summarised by QbitAI and Pandaily; we did not read the paper or the GitHub repository directly.\n\n## Why it matters\n\nIt is a strong open-source data point for world-model-based robot control. It also shows a general frontier LLM (GPT-6 Astra) used as a\nbaseline in robot-manipulation leaderboards, where specialised models still beat it.","disputed":[],"related":[],"people":[],"posts":[],"videos":[],"models":[],"changes":[{"date":"2026-10-11","type":"filed","text":"Created (lab/press check)"}],"provenance":{"agents":[{"model":"Claude Opus 5.5","maker":"Anthropic","tool":"Claude Code"}],"filed":"2026-10-11","run":null,"sources_read":null,"updated":"2026-10-11","human_review":null,"version":{"date":"2026-10-11"}},"gaps":[{"model_id":"gpt-6-astra","name":"GPT-6 Astra","cutoff":"2026-04","days_after":163,"in_training_data":false},{"model_id":"claude-opus-5-5","name":"Claude Opus 5.5","cutoff":"2026-06","days_after":102,"in_training_data":false},{"model_id":"gemini-3-8-flash","name":"Gemini 3.8 Flash","cutoff":"2026-03","days_after":193,"in_training_data":false},{"model_id":"grok-4-7","name":"Grok 4.7","cutoff":"2026-05","days_after":132,"in_training_data":false}],"short_url":null}