[
    {
        "id": "osp-16793",
        "type": "article-journal",
        "title": "Directed Temporal Representations for Offline Visual Control",
        "author": [
            {
                "family": "Yuan",
                "given": "Chenyang"
            },
            {
                "family": "Wang",
                "given": "Haoyu"
            },
            {
                "family": "Sun",
                "given": "Zhuo"
            },
            {
                "family": "Cheng",
                "given": "Xiaoyuan"
            }
        ],
        "URL": "https://omanscience.com/ar/articles/directed-temporal-representations-for-offline-visual-control",
        "language": "en",
        "issued": {
            "date-parts": [
                [
                    2026
                ]
            ]
        },
        "abstract": "Predictive world models provide compact visual representations for control. Control requires a latent geometry aligned with temporal reachability rather than predictive similarity alone. We introduce Directed Temporal Representations for Control (DTRC), which learns such a geometry from offline visual trajectories on top of frozen LeWorldModel (LeWM) features. DTRC constructs a directed temporal quasimetric over the learned control representation. Short-range temporal offsets calibrate the distance scale. Bootstrapped targets extend temporal reachability across longer horizons. Action-conditioned consistency aligns the representation with local transition dynamics. The resulting distance estimates temporal reaching cost, and its change across a transition defines goal-relative temporal progress. We use this progress signal as a temporal critic for direct goal-conditioned policy learning. Model-assisted targets provide an additional training-time refinement under behavior-support and dynamics-agreement constraints. Across ten visual control tasks, DTRC achieves strong goal-conditioned control performance relative to planning and direct-policy baselines. Held-out diagnostics on the four LeWM tasks show consistent short-range temporal calibration, task-dependent long-range and directional structure, and positive transition-level progress. Temporal supervision improves the same flow-policy parameterization across all four LeWM tasks, while the resulting policy acts directly without iterative trajectory search at test time."
    }
]