| --- |
| license: apache-2.0 |
| datasets: |
| - artfawl/VintixDatasetII |
| language: |
| - en |
| pipeline_tag: reinforcement-learning |
| tags: |
| - reinforcement-learning |
| - in-context |
| - action-model |
| --- |
| |
| ## Model Card for Vintix II |
| This is a multi-domain action model via in-context reinforcement learning capable of adaptation to unseen dynamics. |
|
|
| ## Model Description |
| - Developed by: [dunnolab](https://dunnolab.ai) |
| - Demo: [Spaces](https://artfawl-vintix2.hf.space/) |
| - License: Apache 2.0 |
|
|
| ## Model Sources |
| - Repository: https://github.com/dunnolab/vintix-II |
| - Paper: https://arxiv.org/abs/2604.05112 |
|
|
| ## Citation |
| @article{polubarov2026vintixiidecisionpretrained, |
| author={Andrei Polubarov and Lyubaykin Nikita and Alexander Derevyagin and Artyom Grishin and Igor Saprygin and Aleksandr Serkov and Mark Averchenko and Daniil Tikhonov and Maksim Zhdanov and Alexander Nikulin and Ilya Zisman and Albina Klepach and Alexey Zemtsov and Vladislav Kurenkov}, |
| title={Vintix II: Decision Pre-Trained Transformer is a Scalable In-Context Reinforcement Learner}, |
| journal={arXiv}, |
| volume={2604.05112}, |
| year={2026}, |
| } |
