Luddy School of Informatics, Computing, and Engineering, Indiana University, Bloomington(信息学、计算与工程学院,印第安纳大学,布卢明顿);Cognitive Science Program, Indiana University, Bloomington(认知科学项目,印第安纳大学,布卢明顿)
Joshua Nunley
备注:
6 pages, 6 figures. Annual Meeting of the Cognitive Science Society (CogSci 2026)
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.
DeformMaster: An Interactive Physics-Neural World Model for Deformable Objects from Videos
Nankai University(南开大学);Zhejiang University(浙江大学);Southern University of Science and Technology(南方科技大学);Rightly Robotics, A4X(Rightly Robotics,A4X);University of Science and Technology of China(中国科学技术大学)
Carnegie Mellon University(卡内基梅隆大学);University of Pittsburgh(匹兹堡大学);University of California Los Angeles(加州大学洛杉矶分校);Massachusetts General Hospital(麻省总医院);Harvard Medical School(哈佛医学院)
A neural model of the locust visual system for detection of object approaches with real-world scenes
在鸽子和蝗虫等动物的中枢神经系统中,发现了神经元,它们发出信号,指示物体以直接碰撞的方式接近动物。解开避免碰撞的神经电路,并确定潜在的计算原理,是有希望建立基于视觉的神经形态架构,在不久的将来可以在汽车或飞机上找到应用。目前,还没有公布的模型可用于在现实世界条件下的接近物体的鲁棒检测。在这里,我们提出了一个计算架构的信号即将发生的碰撞,蝗虫\emph{lobula giant movement detector}(LGMD)神经元的解剖数据的基础上。即使在不利的情况下,我们的模型也表现出强大的性能,例如接近低对比度的物体,或者具有高度纹理和移动的背景。我们还讨论了哪些组件需要添加到我们的模型,以将其转换为一个成熟的现实世界环境的碰撞检测器。关键词:蝗虫,LGMD,碰撞检测,侧抑制,扩散,开关通路,神经元动力学,计算机视觉,图像处理