认证世界模型作为感知时钟:主动感知的漂移感知截止时间
Certified World Models as Sensing Clocks: Drift-Aware Deadlines for Active Perception
AI总结:
提出一种基于认证世界模型的感知时钟,通过漂移感知的截止时间规则决定主动感知时机,在合成基准和3D VN-JEPA模型上验证了有效性。
摘要:
认证世界模型估计其预测保持有效的时间长度。我们将这个有效期限转化为一个可操作的感知时钟:一个决定智能体何时应停止惯性滑行并重新感知的规则。从一个经过审计的等变世界模型出发,我们推导出无感知间隔的截止时间,并表明学习到的世界模型中的可部署截止时间必须是漂移感知的:仅靠流形上的李雅普诺夫速率会高估惯性滑行的有效性,而校准的原生展开漂移包络则携带部署保证。在一个冻结的3D VN-JEPA模型上,由此产生的时钟控制了跨种子和数据分片的保留间隔同时证书违规。在一个线索条件化的定理台(一个合成基准,其中所有调度器共享精确模型,从而隔离调度规则)上,该时钟在部署分布上保持有效,并在匹配感知预算的情况下,相对于精确混合期望信念调度,显著减少了事件尾违规。我们也报告了局限性:在短视界冻结VN-JEPA机制中,经验共形视界在有效性和预算上与部署时钟匹配,部分重置探索未发现谱项有明确的预算匹配优势。因此,贡献在于一个认证的感知时钟原语和漂移感知部署方法,而非声称谱时钟在经验上支配所有非谱调度器。
英文摘要:
Certified world models estimate how long their predictions remain valid. We turn this validity horizon into an operational sensing clock: a rule for when an agent should stop coasting and re-sense. Starting from an audited equivariant world model, we derive a deadline for no-sensing intervals and show that deployable deadlines in learned world models must be drift-aware: on-manifold Lyapunov rates alone overestimate coasting validity, while calibrated native rollout-drift envelopes carry the deployed guarantee. On a frozen 3D VN-JEPA model, the resulting clock controls held-out interval-simultaneous certificate violation across seeds and data shards. In a cue-conditioned theorem-bed (a synthetic bench where all schedulers share the exact model, isolating the scheduling rule), the clock remains valid on the deployment distribution and substantially reduces eventful-tail violations relative to exact-mixture expected-belief scheduling at matched sensing budget. We also report limits: in the short-horizon frozen VN-JEPA regime, empirical conformal horizons match the deployed clock on validity and budget, and a partial-reset exploration finds no clean budget-matched advantage for the spectral term. Thus the contribution is a certified sensing-clock primitive and drift-aware deployment method, not a claim that spectral clocks empirically dominate all non-spectral schedulers.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。