ProWorld：用于长程视觉目标到达的感知进展双曲世界模型
ProWorld: Progress-Aware Hyperbolic World Models for Long-Horizon Visual Goal Reaching
浏览论文内容
中文总结 AI 辅助
本文针对长程视觉目标到达任务中视觉世界模型的进展感知与轨迹区分难题，提出双曲视觉世界模型ProWorld，经实验相较LeWM实现9.67的平均绝对成功率提升。
中文摘要 AI 辅助
基于JEPA的视觉世界模型通过预测未来隐表示为视觉目标规划提供了有效范式，现有方法通常通过下一步表示预测学习局部转移一致性。然而在长程任务中，仅准确的局部预测无法确保持续向目标推进：一是多步滚动可能保持局部合理性却偏离与目标相关的轨迹；二是局部相似的未来状态可能对应差异显著的长期进展，在主要针对局部一致性优化的隐空间中难以区分。为解决这些挑战，本文引入目标条件进展序，即状态根据向给定目标推进的程度形成的相对排序，该序呈现非对称的由粗到细结构：早期状态保留更广泛的未来可能性，后期状态则聚焦于更具体的目标相关区域，这种结构与双曲几何适配。受此启发，本文提出ProWorld，即感知进展的双曲视觉世界模型，其利用目标条件进展序组织视觉隐空间动力学，通过双曲蕴含学习维持轨迹内的方向进展，通过双曲未来判别缓解局部相似未来状态间的进展歧义。此外，本文设计了感知进展的规划目标，通过联合考虑与目标的接近度及中间状态的持续进展来对候选滚动进行评分。在四个视觉目标到达任务上的实验表明，ProWorld相较LeWM实现了9.67的平均绝对成功率提升，代码将在论文接收后发布。
英文摘要
JEPA-style visual world models offer an effective paradigm for visual goal planning by predicting future latent representations. Existing methods typically learn local transition consistency through next-step representation prediction. However, in long-horizon tasks, accurate local prediction alone need not ensure sustained progress toward the goal. First, multi-step rollouts can remain locally plausible while drifting away from goal-relevant trajectories. Second, locally similar future states can correspond to substantially different long-term progress, making them difficult to distinguish in a latent space optimized mainly for local consistency. To address these challenges, we introduce goal-conditioned progress order, a relative ordering of states according to how they advance toward a given goal. This order exhibits an asymmetric, coarse-to-fine structure: early states retain broader future possibilities, while later states concentrate on more specific goal-relevant regions. Such a structure is well suited to hyperbolic geometry. Motivated by this observation, we propose ProWorld, a progress-aware hyperbolic visual world model. ProWorld leverages goal-conditioned progress order to organize visual latent-space dynamics, maintains directional progress within trajectories via hyperbolic entailment learning, and mitigates progress ambiguity among locally similar future states via hyperbolic future discrimination. Furthermore, we design a progress-aware planning objective that scores candidate rollouts by jointly considering proximity to the goal and sustained progress across intermediate states. Experiments on four visual goal-reaching tasks demonstrate that ProWorld achieves an average absolute success-rate gain of 9.67 over LeWM. The code will be released after the paper is accepted.
