HIJP：用逆向模型替代在线搜索的潜空间规划框架
Beyond Action Prediction: Learning Search-Free Planning in Latent Space
做视觉控制或世界模型方向的朋友可以看看，HIJP 把规划里的在线搜索换成一个逆向模型，成功率 86.8%，速度还能快 1.9 到 16.5 倍。
论文提出 Hindsight Inverse JEPA Planning（HIJP），用目标条件逆向模型直接从当前与目标观测预测动作，替代潜空间世界模型中代价高昂的测试时动作序列优化。训练时通过离线轨迹的未来观测重标注为目标，提供多时间尺度的动作监督，并将预测动作与潜空间预测器对齐以保证动作-转移一致性。推理时交替使用逆向动力学模型和潜空间预测器生成多步动作序列。在四个视觉控制任务上，HIJP 达到 86.8% 总体成功率，规划速度较基于搜索的方法提升 1.9-16.5 倍。
Beyond Action Prediction: Learning Search-Free Planning in Latent Space
Latent world models learn action-conditioned state transitions in a compact representation space, providing a predictive model for visual planning and control. However, planning with these models typically requires costly test-time optimization over action sequences. We propose to replace this online search with a goal-conditioned inverse model that directly predicts actions from current and goal observations. A key challenge is that action prediction alone neither ensures that goal representations encode action-relevant information nor that predicted actions are consistent with the learned latent prediction model. We introduce Hindsight Inverse JEPA Planning (HIJP), a search-free framework that addresses both aspects during training. HIJP relabels future observations along offline trajectories as goals, providing action supervision across multiple temporal horizons. By retaining gradients through the goal representations, this supervision directly shapes the visual representation. HIJP further feeds predicted actions into the latent predictor model and aligns the resulting next-state representations with encoded successor observations, enforcing action-transition consistency. At inference time, the inverse dynamics model and latent predictor models are applied alternately to generate multi-step action sequences without online search. Across four visual control tasks, HIJP achieves 86.8% overall success and a 1.9-16.5x planning speedup over search-based planning.
