用于学习世界模型中反事实滚动的低秩动力学有效潜在载体
Low-Rank Dynamics-Effective Latent Carriers for Counterfactual Rollout in Learned World Models
AI总结：
本文针对学习世界模型的反事实滚动问题，提出基于低秩动力学有效潜在载体的方法，在两物体碰撞环境中验证秩4修补块可实现稳定的12步自主反事实滚动，且效果可复现。
AI中文摘要：
世界模型可预测未来，但无法明确其隐藏状态中哪些部分实际驱动这些预测。本文探究是否可通过小型、可直接处理的隐藏状态变化，将学习到的世界模型置于预期的反事实轨迹上，再让模型自主延续该未来。在受控的两物体二维碰撞环境中，研究人员分析了具有192维隐藏状态的循环世界模型。针对有界局部速度编辑族，首先验证模型可天然表示并滚动编辑后的未来；接着仅从训练集中的事实到反事实隐藏差异构造候选低秩载体，学习从事实状态和请求编辑到载体系数的映射。在预注册的秩网格上，秩4是满足完整开发面板标准的最小测试秩。锚点处的单个秩4修补块足以重定向12步自主滚动，无需未来观测、教师强制或重复修正。该冻结过程在独立训练的检查点上满足预注册复制规则，且在附近干预时间仍可用。随机等范数、错误物体及错误时间的对照无法解释该效果。位置编辑压力测试提供负对照：预期位置修补块可通过原始滚动标准，但无修补块和随机对照也能通过相同标准，且未建立错误物体特异性。因此，仅成功编辑不足够。本文用“动力学有效”描述一种干预，该干预在自主滚动下以持续且目标特定的方式改变模型的未来计算。秩4结果确定了测试速度编辑族的紧凑干预界面，而非封闭的四维状态或固有状态维度。
英文摘要：
We ask whether a small, directly addressable hidden-state intervention can place a learned world model on an intended counterfactual future and then let the model's own dynamics carry that future forward. In a controlled two-object collision environment, we study a 192-dimensional recurrent model trained on factual and locally edited counterfactual trajectories. Candidate carriers are learned from training-only counterfactual-minus-factual hidden differences, and an affine map predicts carrier coordinates from the factual state and requested edit without access to the native counterfactual hidden state at test time. For bounded single-component velocity edits, rank 4 is the smallest tested rank on the preregistered grid that satisfies the development criteria. A one-shot rank-4 patch launches a 12-transition autonomous rollout without future observations, teacher forcing, repeated hidden-state correction, or physical-state clamping. The frozen procedure satisfies the preregistered 2-of-3 fresh-checkpoint replication rule and remains reusable at nearby anchors. The same Single-derived carrier and Single-only affine map also support bounded same-object two-component requests. Across the matched training regimes, broader counterfactual support was associated mainly with better Joint rollout accuracy and more additive Joint hidden responses. Composition-related structure is enriched in the rank-4 subspace but is not confined to it, and local recurrent diagnostics show strong one-step coupling from the carrier to the rest of the hidden state. A position-edit stress test fails the required specificity controls. Together, these results support a compact dynamics-effective intervention-entry interface, not a closed four-dimensional state or an intrinsic state dimension.
