用空间结构保持感知拓扑，让神经场实现带身体的物理预测与离线学习。
Neural Fields as World Models
- 用运动门控神经场保留空间拓扑，让物理预测变成几何传播。
- 在3个实验中实现无跳跃的弹道预测、离线优化抓取策略、自动生成体感运动通道。
- 适合对具身智能、世界模型、神经表征感兴趣的研究者。
人类在离线状态下预演未来，如心理练习或做梦，暗示世界模型可支持脱离环境的任务学习。标准机器学习世界模型将视觉输入压缩为隐向量，丢失了感知皮层所具有的空间结构。我们提出同构世界模型：保持感官拓扑的架构，使物理预测变为几何传播而非抽象状态转移。通过运动门控神经场实现该思想，其中活动通过局部侧向连接演化，运动指令乘性调制特定通道。在三个实验中，同一架构实现了无“瞬移”的弹道预测，通过冻结的已学世界模型离线传播任务误差以改进抓取策略，并在无身体标签情况下发展出体感选择性运动通道。这些结果初步表明，物理预测、离线任务学习和身体关联表征共享同一计算基础：基于动作条件的空间地图中的预测。
原文摘要 · Abstract (English)
Humans rehearse possible futures offline, as in mental practice and perhaps dreaming, suggesting that world models may support task learning away from the environment. Standard machine learning world models compress visual input into latent vectors, discarding the spatial structure that characterizes sensory cortex. We propose isomorphic world models: architectures that preserve sensory topology, so physics prediction becomes geometric propagation rather than abstract state transition. We implement this idea with motor-gated neural fields, where activity evolves through local lateral connectivity and motor commands multiplicatively modulate specific channels. Across three experiments, the same architecture learns ballistic prediction without ``teleporting,'' improves a catching policy offline by propagating task error through a frozen learned world model, and develops body-selective motor channels without body labels. These results provide preliminary evidence that physical prediction, offline task learning, and body-linked representation share a common computational substrate: action-conditional prediction within a spatial map.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。