[
    {
        "id": "osp-21386",
        "type": "article-journal",
        "title": "One-Step Generative Modeling via Training Dynamics Action",
        "author": [
            {
                "family": "Liang",
                "given": "Zhangyong"
            },
            {
                "family": "Huang",
                "given": "Ying"
            },
            {
                "family": "Ling",
                "given": "Haibin"
            }
        ],
        "URL": "https://omanscience.com/ar/articles/one-step-generative-modeling-via-training-dynamics-action",
        "language": "en",
        "issued": {
            "date-parts": [
                [
                    2026
                ]
            ]
        },
        "abstract": "One-step generative models construct a static generator through iterative training-time transport. Existing transport objectives primarily assess distributional motion, although a neural generator needs to realize the requested sample displacements jointly through shared parameter updates. The training-time construction raises the question: \\emph{once training becomes the iterative process that constructs the final one-step map, what to optimize: the next distributional move, or the route by which the finite generator learns the final map?} To address the question, we introduce \\textbf{T}raining \\textbf{D}ynamics \\textbf{A}ction (\\textbf{TDAction}), which selects transport targets according to local shared-parameter realization cost while retaining a prescribed level of distributional progress. We formulate the cost as a soft-terminal control problem and derive a closed-form Batch Tangent Action-to-Go value that accounts for parameter effort and terminal mismatch. The criterion captures cross-sample interactions omitted by independent pairwise costs; under isotropic mobility, the criterion agrees with quadratic Euclidean assignment for deterministic balanced couplings. Randomized tangent probes provide a low-rank implementation that constructs shared detached targets without adding an inference-time trajectory. Controlled studies examine the relationship between generator geometry, transport selection, and realized local action. On ImageNet $256\\times256$, TDAction attains an FID below $1.1$ without distillation."
    }
]