Zero-shot World Models Are Developmentally Efficient Learners

• URL: http://arxiv.org/abs/2604.10333v1
• Date: Sat, 11 Apr 2026 19:32:33 GMT
• Title: Zero-shot World Models Are Developmentally Efficient Learners
• Abstract summary: Young children demonstrate early abilities to understand their physical world.<n>We introduce a novel computational hypothesis for these abilities, the Zero-shot Visual World Model.<n>We show that ZWM can be learned from the first-person experience of a single child.
• Score: 8.29886792024518
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Young children demonstrate early abilities to understand their physical world, estimating depth, motion, object coherence, interactions, and many other aspects of physical scene understanding. Children are both data-efficient and flexible cognitive systems, creating competence despite extremely limited training data, while generalizing to myriad untrained tasks -- a major challenge even for today's best AI systems. Here we introduce a novel computational hypothesis for these abilities, the Zero-shot Visual World Model (ZWM). ZWM is based on three principles: a sparse temporally-factored predictor that decouples appearance from dynamics; zero-shot estimation through approximate causal inference; and composition of inferences to build more complex abilities. We show that ZWM can be learned from the first-person experience of a single child, rapidly generating competence across multiple physical understanding benchmarks. It also broadly recapitulates behavioral signatures of child development and builds brain-like internal representations. Our work presents a blueprint for efficient and flexible learning from human-scale data, advancing both a computational account for children's early physical understanding and a path toward data-efficient AI systems.

Related papers

• Minimal Embodiment Enables Efficient Learning of Number Concepts in Robot [44.96166832110118]
  How intelligent systems acquire abstract numerical concepts from sensorimotor experience remains a fundamental challenge in cognitive science and artificial intelligence.<n>Here we investigate embodied numerical learning using a neural network model trained to perform sequential counting through naturalistic robotic interaction with a Franka Panda manipulator.<n>We demonstrate that embodied models achieve 96.8% counting accuracy with only 10% of training data, compared to 60.6% for vision-only baselines.
  arXiv  Detail & Related papers  (2026-04-13T12:14:58Z)
• A Brain-like Synergistic Core in LLMs Drives Behaviour and Learning [50.68188138112555]
  We show that large language models spontaneously develop synergistic cores.<n>We find that areas in middle layers exhibit synergistic processing while early and late layers rely on redundancy.<n>This convergence suggests that synergistic information processing is a fundamental property of intelligence.
  arXiv  Detail & Related papers  (2026-01-11T10:48:35Z)
• The Imperfect Learner: Incorporating Developmental Trajectories in Memory-based Student Simulation [55.722188569369656]
  This paper introduces a novel framework for memory-based student simulation.<n>It incorporates developmental trajectories through a hierarchical memory mechanism with structured knowledge representation.<n>In practice, we implement a curriculum-aligned simulator grounded on the Next Generation Science Standards.
  arXiv  Detail & Related papers  (2025-11-08T08:05:43Z)
• Less is More: some Computational Principles based on Parcimony, and Limitations of Natural Intelligence [39.89179121430488]
  Natural intelligence consistently achieves more with less.<n>Today's AI relies on virtually unlimited computational power, energy, and data to reach high performance.<n>This paper argues that constraints in NI are paradoxically catalysts for efficiency, adaptability, and creativity.
  arXiv  Detail & Related papers  (2025-06-08T09:42:29Z)
• Core Knowledge Deficits in Multi-Modal Language Models [41.422258645731276]
  Multi-modal Large Language Models (MLLMs) demonstrate impressive abilities over high-level perception and reasoning.<n>But their robustness in the wild remains limited, often falling short on tasks that are intuitive and effortless for humans.<n>We examine the hypothesis that these deficiencies stem from the absence of core knowledge--rudimentary cognitive abilities innate to humans from early childhood.
  arXiv  Detail & Related papers  (2024-10-06T20:13:11Z)
• The BabyView dataset: High-resolution egocentric videos of infants' and young children's everyday experiences [8.952954042940368]
  This dataset includes egocentric videos from children spanning 6 months to 3 years of age in longitudinal, at-home contexts.<n>We train self-supervised language and vision models and evaluate their transfer to out-of-distribution tasks.<n>Our dataset stands as an open challenge for robust, human-like AI systems.
  arXiv  Detail & Related papers  (2024-06-14T23:52:27Z)
• JECC: Commonsense Reasoning Tasks Derived from Interactive Fictions [75.42526766746515]
  We propose a new commonsense reasoning dataset based on human's Interactive Fiction (IF) gameplay walkthroughs. Our dataset focuses on the assessment of functional commonsense knowledge rules rather than factual knowledge. Experiments show that the introduced dataset is challenging to previous machine reading models as well as the new large language models.
  arXiv  Detail & Related papers  (2022-10-18T19:20:53Z)
• A Benchmark for Compositional Visual Reasoning [5.576460160219606]
  We introduce a novel visual reasoning benchmark, Compositional Visual Relations (CVR), to drive progress towards more data-efficient learning algorithms. We take inspiration from fluidic intelligence and non-verbal reasoning tests and describe a novel method for creating compositions of abstract rules and associated image datasets at scale. Our proposed benchmark includes measures of sample efficiency, generalization and transfer across task rules, as well as the ability to leverage compositionality.
  arXiv  Detail & Related papers  (2022-06-11T00:04:49Z)
• A Minimalist Dataset for Systematic Generalization of Perception, Syntax, and Semantics [131.93113552146195]
  We present a new dataset, Handwritten arithmetic with INTegers (HINT), to examine machines' capability of learning generalizable concepts. In HINT, machines are tasked with learning how concepts are perceived from raw signals such as images. We undertake extensive experiments with various sequence-to-sequence models, including RNNs, Transformers, and GPT-3.
  arXiv  Detail & Related papers  (2021-03-02T01:32:54Z)
• HALMA: Humanlike Abstraction Learning Meets Affordance in Rapid Problem Solving [104.79156980475686]
  Humans learn compositional and causal abstraction, ie, knowledge, in response to the structure of naturalistic tasks. We argue there shall be three levels of generalization in how an agent represents its knowledge: perceptual, conceptual, and algorithmic. This benchmark is centered around a novel task domain, HALMA, for visual concept development and rapid problem-solving.
  arXiv  Detail & Related papers  (2021-02-22T20:37:01Z)
• A Competence-aware Curriculum for Visual Concepts Learning via Question Answering [95.35905804211698]
  We propose a competence-aware curriculum for visual concept learning in a question-answering manner. We design a neural-symbolic concept learner for learning the visual concepts and a multi-dimensional Item Response Theory (mIRT) model for guiding the learning process. Experimental results on CLEVR show that with a competence-aware curriculum, the proposed method achieves state-of-the-art performances.
  arXiv  Detail & Related papers  (2020-07-03T05:08:09Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.