[
    {
        "id": "osp-25866",
        "type": "article-journal",
        "title": "VLaRL: Augmenting Vision-Language-Action Models with Simulation-Trained Latent-Conditioned Residual RL",
        "author": [
            {
                "family": "Saito",
                "given": "Namiko"
            },
            {
                "family": "Kim",
                "given": "Kinam"
            },
            {
                "family": "Kim",
                "given": "Heecheol"
            },
            {
                "family": "Ikeuchi",
                "given": "Katsushi"
            },
            {
                "family": "Matsushita",
                "given": "Yasuyuki"
            }
        ],
        "URL": "https://omanscience.com/en/articles/vlarl-augmenting-vision-language-action-models-with-simulation-trained-latent-conditioned-residual-rl",
        "language": "en",
        "issued": {
            "date-parts": [
                [
                    2026
                ]
            ]
        },
        "abstract": "Vision-language-action (VLA) models provide broad, instruction-conditioned manipulation behaviors, but their physical execution can remain imprecise during contact-rich interaction. Residual reinforcement learning (RL) can correct such errors while keeping the VLA frozen, but real-robot RL is costly and safety-critical. We propose VLA Latent-Conditioned RL (VLaRL), which enables residual RL for frozen VLAs to be trained in simulation and deployed on real robots without real-world RL or online adaptation. The key challenge is transferring the learned residual policy despite the visual gap between simulation and reality. Rather than requiring pixel-level visual correspondence, VLaRL uses the VLA's internal vision-language latent representation to condition residual control and as the sim-to-real transfer interface, and learns a lightweight mapper that transforms simulation-derived latents toward the real latent distribution. Across four contact-rich manipulation tasks and two VLA backbones, VLaRL improves real-world success in all task-backbone combinations, while controlled ablations demonstrate the importance of both latent conditioning and latent alignment for transferring simulation-trained residual control."
    }
]