[
    {
        "id": "osp-25530",
        "type": "article-journal",
        "title": "Discrete Forcing: Infusing Discrete Guidance into Continuous Denoising for Few-Step Action Experts",
        "author": [
            {
                "family": "Wang",
                "given": "Jingbo"
            },
            {
                "family": "Song",
                "given": "Wenxuan"
            },
            {
                "family": "Yu",
                "given": "Wenhao"
            },
            {
                "family": "Zhao",
                "given": "Han"
            },
            {
                "family": "Wang",
                "given": "Xi"
            },
            {
                "family": "Chen",
                "given": "Jiayi"
            },
            {
                "family": "Wang",
                "given": "Donglin"
            },
            {
                "family": "Wang",
                "given": "Yan"
            },
            {
                "family": "Li",
                "given": "Haoang"
            }
        ],
        "URL": "https://omanscience.com/en/articles/discrete-forcing-infusing-discrete-guidance-into-continuous-denoising-for-few-step-action-experts",
        "language": "en",
        "issued": {
            "date-parts": [
                [
                    2026
                ]
            ]
        },
        "abstract": "Efficient action generation in vision-language-action (VLA) models requires capturing both coarse action structure and fine-grained details. Discrete action tokens provide compact structural representations but sacrifice precision, while continuous action tokens offer high precision but often require multiple denoising steps. We introduce Discrete Forcing, a flow-matching framework that combines these representations through an explicit coarse-to-fine generation process. It first predicts discrete action tokens to establish a coarse action structure, then uses them to guide continuous action refinement. The discrete and continuous components share a common diffusion transformer backbone with specialized branches, maintaining a parameter count comparable to a conventional single-branch model while requiring only one forward pass per branch. Extensive evaluations across multiple benchmarks demonstrate improved performance and faster inference over a parameter-matched continuous action expert, with consistent performance gains as model capacity increases. Real-world experiments further demonstrate improvements on high-precision and dynamic manipulation tasks."
    }
]