{"id":"f8b378da-d4b0-4c84-af50-d7ce909ba834","slug":"dyna-2","name":"DYNA-2","description":"DYNA-2 is Dyna Robotics' flagship World-Action Model (WAM), pre-trained on over 1 million hours of human egocentric video — roughly 170 years of continuous waking experience. Unlike VLA (Vision-Language-Action) models, DYNA-2 is built on a video-diffusion backbone that jointly denoises future video and future actions, enabling physical intuition and spatial reasoning to transfer directly from human video to robot hardware without any robot data in pre-training. Announced August 10, 2026, it demonstrates the first human-to-robot scaling law: robot performance improves smoothly and predictably with every added hour of human data, without hitting plateaus. DYNA-2 enables zero-shot performance at production-level speeds across new deployment sites, and can be adapted to new robot platforms with just a few hours of local fine-tuning. In one benchmark, 13 minutes of data was sufficient for DYNA-2 to command five-fingered robot hands to twist open a bottle cap.","brainType":"world-model","isOpen":false,"maturityStage":null,"architecture":null,"reviewStatus":"unreviewed","sources":[{"url":"https://www.dyna.co/dyna-2","title":"Dyna-2: A 1-Million-Hour Scaling Law for World-Action Models","sourceName":"Dyna Robotics (official)"},{"url":"https://www.prnewswire.com/news-releases/dyna-robotics-unveils-dyna-2-world-action-model-demonstrating-first-true-scaling-law-in-robotics-powered-entirely-by-human-data-302847114.html","title":"Dyna Robotics unveils DYNA-2 World-Action Model","sourceName":"PR Newswire"}],"keyFacts":[{"Brain type":"World-Action Model (WAM) — video-diffusion backbone"},{"Pre-training data":"1,000,000+ hours of human egocentric video (~170 years of continuous waking experience)"},{"Architecture":"Dual next-frame and next-action world-modeling; jointly denoises future video and future actions"},{"Paradigm shift":"First human-to-robot scaling law — performance scales smoothly with human video data, no plateaus"},{"Fine-tuning":"Adapts to new robot platforms with hours of local data (13 min for bottle-cap task)"},{"Key result":"133% improvement on instruction-following tasks via video co-training; zero-shot production-level performance"},{"Announced":"August 10, 2026"},{"Predecessor":"DYNA-1 (foundation-model, April 2025)"}],"aliases":[],"collisionRisk":"low","reviewNote":null,"builtOnBrainId":null,"createdAt":"2026-08-11T01:45:18.941Z","updatedAt":"2026-08-11T01:45:18.941Z","jsonLd":{"@context":"https://schema.org","@type":"SoftwareApplication","@id":"https://registry.deploy.report/brains/dyna-2","url":"https://registry.deploy.report/brains/dyna-2","name":"DYNA-2","description":"DYNA-2 is Dyna Robotics' flagship World-Action Model (WAM), pre-trained on over 1 million hours of human egocentric video — roughly 170 years of continuous waking experience. Unlike VLA (Vision-Language-Action) models, DYNA-2 is built on a video-diffusion backbone that jointly denoises future video and future actions, enabling physical intuition and spatial reasoning to transfer directly from human video to robot hardware without any robot data in pre-training. Announced August 10, 2026, it demonstrates the first human-to-robot scaling law: robot performance improves smoothly and predictably with every added hour of human data, without hitting plateaus. DYNA-2 enables zero-shot performance at production-level speeds across new deployment sites, and can be adapted to new robot platforms with just a few hours of local fine-tuning. In one benchmark, 13 minutes of data was sufficient for DYNA-2 to command five-fingered robot hands to twist open a bottle cap.","identifier":"f8b378da-d4b0-4c84-af50-d7ce909ba834","applicationCategory":"world-model","publisher":{"@id":"https://deploy.report/#organization"}},"framework_metadata":{"framework_schema_version":"0.1.0","verification_status":"unreviewed","maturity_stage":null,"lifecycle_state":null,"architectural_position":{"cohort":null,"sub_cohorts":[]},"within_cohort_verified_vs_claimed_pair":null,"cap_flags":[],"verification_depth":{"sources_count":2,"primary_source_types":["primary-company-ir"]}}}