← 研踪 PaperTrailarXiv:2611.25679 · v1
LeCompass: Task-Level Execution through State-Indexed Interfaces
首次提交 2026-11-19 15:57
版本更新 2026-11-19 15:57
雷达观测 2026-11-20 19:58
摘要
Action-conditioned joint-embedding predictive architectures (JEPAs) offer a foundation for predictive decision-making by modeling the consequences of actions in representation space. Yet evaluating local reachability in latent space does not by itself provide a task-level execution interface: intermediate targets must be generated, local inference has finite budgets, and execution requires spatial feedback and persistent interaction state. We introduce LeCompass, a state-indexed execution framework built around a frozen LeWorldModel (LeWM). A proposer supplies intermediate latent targets, while CompassFlow searches the source space of a learned trajectory prior to obtain effective action candidates under limited predictive-evaluation budgets. Patch-token readouts provide spatial feedback, while observation-based memory supports phase transitions and bounded recovery. State-indexed targets support cross-episode context-goal composition. On 1,000 official TEST full-episode Cube trials, the complete LeCompass execution system achieves 86.9% native 4-cm reach. Separate matched analyses show that predictive ranking raises success from 4.7% to 44.9% on TEST PushT and from 33.8% to 77.7% on TEST TwoRoom. These results demonstrate task-level execution with task-dependent roles for latent target proposal, predictive search, and observation-grounded control.
作者备注:33 pages, 8 figures
观测到的版本
相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。
v1 · 2026-11-19 15:57 · 最新观测版本
LeCompass: Task-Level Execution through State-Indexed Interfaces
Action-conditioned joint-embedding predictive architectures (JEPAs) offer a foundation for predictive decision-making by modeling the consequences of actions in representation space. Yet evaluating local reachability in latent space does not by itself provide a task-level execution interface: intermediate targets must be generated, local inference has finite budgets, and execution requires spatial feedback and persistent interaction state. We introduce LeCompass, a state-indexed execution framework built around a frozen LeWorldModel (LeWM). A proposer supplies intermediate latent targets, while CompassFlow searches the source space of a learned trajectory prior to obtain effective action candidates under limited predictive-evaluation budgets. Patch-token readouts provide spatial feedback, while observation-based memory supports phase transitions and bounded recovery. State-indexed targets support cross-episode context-goal composition. On 1,000 official TEST full-episode Cube trials, the complete LeCompass execution system achieves 86.9% native 4-cm reach. Separate matched analyses show that predictive ranking raises success from 4.7% to 44.9% on TEST PushT and from 33.8% to 77.7% on TEST TwoRoom. These results demonstrate task-level execution with task-dependent roles for latent target proposal, predictive search, and observation-grounded control.
查看此版本解读 →查看此版本原文 ↗