World models are increasingly used to simulate physical interactions, but training a separate model for each environment limits scalability. Cross-environment prediction requires identifying the current physical rule, which appearance alone may not reveal. We therefore study visual calibration: using object motion and interactions in a short video as direct evidence to infer the current rule and predict motion under that rule from a different initial state. However, differences in data availability across physical conditions can yield a long-tailed training distribution, biasing models toward common rules even when evidence supports rare ones. To study this challenge, we introduce TailWorld, which evaluates the transfer of demonstrated rules across initial states while independently controlling training imbalance and calibration informativeness. The benchmark compares predictions with two reference futures from the same prediction initial state, one following the demonstrated rule and the other a common rule, to measure prediction bias toward common dynamics. We further propose Rule Inference for Transfer (RIFT), which learns how different rules affect object motion, infers the current rule from calibration interactions, and applies it to prediction from a new initial state. RIFT explicitly controls the influence of training frequency on rule inference, allowing sufficiently informative observational evidence to support rare rules. Experiments on TailWorld show that RIFT improves prediction accuracy and physical consistency across varying training imbalances and distribution shifts, with gains in predicting rare dynamics.
Visual Explanations from Hadamard Product in Multimodal Deep Networks
Seoul National University(首尔大学)
对模型学习表征的直观解释有助于理解学习的基本原理。以前的作品中的注意力模型用于在图像或文本上使用它们的学习权重来可视化关注区域,以确认它们的预期机制。Kim et al.(2016)表明,多模态深度网络中的Hadamard产品,以视觉问答任务的联合功能而闻名,隐含地执行视觉输入的注意机制。在这项工作中,我们扩展了他们的工作,以表明多模态深度网络中的Hadamard乘积不仅适用于视觉输入,而且还适用于文本输入,同时使用所提出的基于梯度的可视化技术。阿达玛产品的注意力效果可视化视觉和文本输入通过分析两个输入和输出的阿达玛产品与所提出的方法,并与学习的视觉问答模型的注意力权重进行比较。
TAVAE: A VAE with Adaptable Priors Explains Contextual Modulation in the Visual Cortex
Department of Computational Sciences(计算科学系);HUN-REN Wigner Research Centre for Physics(霍恩-伦维格物理研究中心);Princeton Neuroscience Institute(普林斯顿神经科学研究所);Princeton University(普林斯顿大学);Center for Molecular and Behavioral Neuroscience(分子与行为神经科学中心);Rutgers University(罗格斯大学)
Learning Concept-Based Causal Transition and Symbolic Reasoning for Visual Planning
Beijing Institute for General Artificial Intelligence (BIGAI)(北京通用人工智能研究院(BIGAI));Institute for Artificial Intelligence, Peking University(北京大学人工智能研究院);Yuanpei College, Peking University(北京大学元培学院);University of California, Los Angeles (UCLA)(加利福尼亚大学洛杉矶分校)