Green-VLA: Staged Vision-Language-Action Model for Generalist Robots

Ivan Apanasevich, Mikhail Artemyev, Ruslan Babakyan, Polina Fedotova, D. Grankin, Egor Kupryashin, Anastas Misailidi, Daniil, Alexander Nutalapati, Gena Sidorov, Ivan Efremov, Matvey Gerasyov, D. Pikurov, Yuriy Senchenko, Sergei Davidenko, Daniil Kulikov, Maxim, Kazybek A, Oleg Shamanin, D. Statovoy, Eduard, Zorin Ilya, A. Letkin, Egor Rusakov, A. Silchenko, Vlad Vorobyov, SERGEI, Aleksey Postnikov

Green-VLA: Staged Vision-Language-Action Model for Generalist Robots: 322 upvotes on Hugging Face Daily Papers, #1 of 73 papers on 2026-02-03. Day-by-day upvote history.

We introduce Green-VLA, a staged Vision-Language-Action (VLA) framework for real-world deployment on the Green humanoid robot while maintaining generalization across diverse embodiments. Green-VLA follows a five stage curriculum: (L0) foundational VLMs, (L1) multimodal grounding, (R0) multi-embodiment pretraining, (R1) embodiment-specific adaptation, and (R2) reinforcement-learning (RL) policy alignment. We couple a scalable data-processing pipeline (3,000 hours of demonstrations) with temporal alignment and quality filtering, and use a unified, embodiment-aware action interface enabling a single policy to control humanoids, mobile manipulators, and fixed-base arms. At inference, the VLA controller is enhanced with episode-progress prediction, out-of-distribution detection, and joint-prediction-based guidance to improve safety and precise target selection. Experiments on Simpler BRIDGE WidowX and CALVIN ABC-D, as well as real-robot evaluations, show strong generalization and performance gains from RL alignment in success rate, robustness, and long-horizon efficiency.

Paper page on Hugging Face · arXiv

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.