[
    {
        "id": "osp-18091",
        "type": "article-journal",
        "title": "ExStereo: Lifting 2D Vision-Language-Action Models to 3D with Explicit Stereo Representations",
        "author": [
            {
                "family": "Liu",
                "given": "I-Chun Arthur"
            },
            {
                "family": "Chen",
                "given": "Jason"
            },
            {
                "family": "Sukhatme",
                "given": "Gaurav S."
            },
            {
                "family": "Seita",
                "given": "Daniel"
            }
        ],
        "URL": "https://omanscience.com/en/articles/exstereo-lifting-2d-vision-language-action-models-to-3d-with-explicit-stereo-representations",
        "language": "en",
        "issued": {
            "date-parts": [
                [
                    2026
                ]
            ]
        },
        "abstract": "Three-dimensional perception is critical for robotic manipulation, particularly for high-precision tasks, as recovering metric depth and precise 3D object positions from monocular RGB observations is inherently ill-posed. However, many Vision-Language-Action (VLA) models rely solely on RGB observations for perception. Leveraging recent advances in foundation models for stereo matching, we introduce ExStereo, a stereo module that augments pre-trained 2D VLAs with 3D perception. ExStereo reconstructs scene geometry from stereo image pairs and renders multi-view observations as an explicit stereo representation for stereo feature extraction. The action tokens from the action expert selectively attend to the resulting stereo tokens through our proposed action-stereo cross-attention mechanism, enabling the policy to generate robot actions conditioned on 3D scene information. To learn robust 3D representations, we introduce a mid-training stage before task-specific post-training, using a self-supervised learning objective on large-scale stereo data. We validate our approach by fine-tuning two publicly available VLAs, $π_{0.5}$ and SmolVLA, and evaluate them in simulation and on a real-world bimanual PiPER platform. Across both settings, VLAs fine-tuned with ExStereo consistently outperform baselines, demonstrating the effectiveness of stereo perception for robotic manipulation. Our project website is at: https://exstereo-vla.github.io/ExStereo/."
    }
]