Child and Animal Learning Development

Latest papers

• Generalization and Memorization along the Learning Trajectory of Neural Language Models: A Geometric Account of Categorization

  Wang Bojun, Holly Jenkins, Elizabeth Wonnacott · 30 September 2026

  We investigate how generalization and memorization develop along the learning trajectory of neural language models. Using controlled synthetic grammars, we examine both the geometry of representation space and model behaviour over training. We find that continuous regions of representation space not…

• A Unified Account of Concepts and Chunks

  Karthik Singaravadivelan, Pat Langley · 28 September 2026

  Cognitive psychology has studied how people encode, use, and learn concepts that describe categories, and how they represent, recognize, and acquire chunks for familiar patterns of elements. The literatures on these two topics are nearly disjoint, which poses a challenge for unified theories of cogn…

• World Modeling in Transformers

  Pierre Beckmann, Matthieu Queloz, Andre Freitas · 21 September 2026

  Behavioral failures can make a transformer appear to lack a world model even when it has learned faithful representations of its environment. We demonstrate this in TaxiGPT, a transformer trained on random walks through Manhattan whose failures have been interpreted as evidence of an incoherent inte…

• CogGym: Towards Large-Scale Comparative Evaluation of Human and Machine Cognition

  Lance Ying, Jinzhou Wu, Yingshan Susan Wang, Shivam Aarya, Luca M. Schulze Buschoff, Harry Chen, Katherine M. Collins, Andrea de Varda, Shuhao Fu, Sean Dae Houlihan, Akshay K. Jagadish, Guangyuan Jiang, Samuel Kiegeland, Tetsu Kurumisawa, Rongzhi Liu, Ryan Liu, Ningshan Ma, Kathryn McGregor, Younes Strittmatter, Polina Tsvilodub, Jacob Hoover Vigly, Sarah Wu, Enjie Xu, Yiling Yun, Kelsey Allen, Tyler Brooke-Wilson, Brian Christian, Evelina Fedorenko, Michael C. Frank, Michael Franke, Tao Gao, Samuel J. Gershman, Robert D. Hawkins, Jennifer Hu, Julian Jara-Ettinger, Max Kleiman-Weiner, Sydney Levine, Tal Linzen, Hongjing Lu, Timothy O'Donnell, Desmond C. Ong, Steven T. Piantadosi, Rebecca Saxe, Eric Schulz, Tianmin Shu, Felix A. Sosa, Ilia Sucholutsky, Tan Zhi-Xuan, Tomer Ullman, Fei Xu, Ilker Yildirim, Jian-Qiao Zhu, Thomas L. Griffiths, Tobias Gerstenberg, Kevin Smith, Joshua B. Tenenbaum · 21 September 2026

  Understanding and modeling human intelligence are parallel goals shared by artificial intelligence (AI) and cognitive science. As AI systems grow increasingly capable, in what ways do model responses resemble human responses, and where do they systematically diverge? The sheer breadth and diversity …

• Thought without systematicity? Evaluating reasoning models on rule induction tasks

  Simon Schug, Brenden M. Lake · 15 September 2026

  A central tenet of human cognition is systematicity, the principle that understanding one concept is inherently tied to understanding close variations of that concept. Do reasoning models robustly exhibit such systematicity? If so, we would expect consistent performance on structurally equivalent va…

• Map Users and Mapmakers: The Scope of Cognitive Attribution from Acquired Representations

  Yiling Wu · 15 September 2026

  An acquired representation can enlarge a system's cognitive repertoire without transferring the capacities exercised in producing that representation. This paper develops a framework for specifying that enlargement and its limits. Its central contribution is a five-part attribution table distinguish…

• Sparks of In Silico Cognitive Science: Theories from Simulated Data Can Generalize to Humans

  Akshay K. Jagadish, Younes Strittmatter, Nori Jacoby, Eric Schulz, Nathaniel Daw, Thomas L. Griffiths, Suyog H. Chandramouli · 9 September 2026

  Behavioral foundation models have been proposed as stand-ins for human participants across settings, but it is unclear whether theories discovered on them generalize to humans or merely characterize the simulator. We ran the Automated Cognitive Scientist (\textsc{AutoCog}), a closed-loop discovery s…

• Learning Counterfactual World Models for Embodied Reasoning under Partial Observability

  Todd Y. Zhou, Daniel Zhang · 9 September 2026

  World models promise a general route to embodied intelligence: learn predictive dynamics once, then reason, plan, and act with them. Increasingly, the representations beneath such models are pretrained on large-scale video, interaction, and multimodal corpora, which raises a question prediction qual…

• What Is Worth Representing? Representational Empowerment for Continual Model Construction

  Fei Dai, Hanqi Zhou, Alison Gopnik, Charley Wu · 3 September 2026

  The first problem of modeling the world is not just estimating the right parameters or causal structure, but deciding what should be represented at all. We frame this problem as continual model construction: an agent maintains an environment-specific model M of an inaccessible world W and curates a …

• Induction and Inquiry via Probabilistic Reasoning over Language and Code

  Wasu Top Piriyakulkij, Sam Acquaviva, Cassidy Langenfeld, Joshua Tenenbaum, Kevin Ellis · 3 September 2026

  How humans grow and maintain abstract knowledge from the sparse, streaming noisy data of experience is a longstanding challenge in cognitive science. Any computational account must satisfy at least three desiderata: It must be (1) data-efficient and compute-efficient, (2) capture gradations of uncer…

• Infer Human's Intentions Before Following Natural Language Instructions

  Yanming Wan, Yue Wu, Yiping Wang, Jiayuan Mao, Natasha Jaques · 27 August 2026

  For AI agents to be helpful to humans, they should be able to follow natural language instructions to complete everyday cooperative tasks in human environments. However, real human instructions inherently possess ambiguity, because the human speakers assume sufficient prior knowledge about their hid…

• Platonic Representation Hypothesis on World Models

  Wenhow Li (The Hong Kong University of Science and Technology), Chengwei MA (The Hong Kong University of Science and Technology), Hui Xiong (The Hong Kong University of Science and Technology), Ying-Cong Chen (The Hong Kong University of Science and Technology), Lei Zhang (The Hong Kong University of Science and Technology) · 26 August 2026

  World models have demonstrated significant potential for perceiving and simulating complex environments. Despite their strong performance, the fundamental nature of their learned representations remains poorly understood. In this paper, we investigate the Platonic Representation Hypothesis within th…

• Behaviour Is an Incomplete Measure of Reasoning Development: Cross-surface pre-arrival accessibility and the limits of developmental inference in a recurrent-depth reasoner

  Simon Lam-Muir · 18 August 2026

  Capability development is routinely inferred from behavioural thresholds, from final checkpoints, or from what a decoder can read out of a hidden state. These quantities need not identify the same event. We study a 30M-parameter recurrent-depth relational reasoner in a closed, oracle-defined world, …

• When Do Concepts Become Functionally Sufficient During Language-Model Training?

  Raphael Bernas, Paul G. Chevalier, Fanny Jourdan, Céline Hudelot · 18 August 2026

  Understanding a model and its learning mechanisms in depth requires identifying when its internal structures become useful, rather than simply looking at the final state. We study this through concept dynamics: at each layer and checkpoint, we decompose activations, select sparse soft masks, and inj…

• A Unifying Perspective on Causal World Models: From Observations to Representations to Structure

  Avinash Kori, Fabrizio Russo · 14 August 2026

  World Models (WM) are increasingly seen as a foundation for intelligent agents that can predict, plan, and act beyond their training distribution. In this paper, we study WMs from a causal perspective across multiple levels of abstraction, ranging from perceptual observations to building a conceptua…

• On the use of foundation models in cognitive science

  Raj Sanjay Shah, Alex Warstadt, Michael Frank, Sashank Varma · 11 August 2026

  A host of recent studies have evaluated the cognitive and developmental alignment of Foundation Models (FMs). These investigations include evaluations of their correspondence to adult performance across a range of cognitive domains, as well as whether aspects of model training track children's cogni…

• Evaluating Theory of Mind in Reasoning Models: Robustness over Reasoning

  Ian B. de Haan, Peter van der Putten, Max van Duijn · 6 August 2026

  Large language models (LLMs) have recently shown strong performance on Theory of Mind (ToM) tests, prompting debate about the nature and validity of the underlying capabilities. At the same time, reasoning-oriented LLMs trained via reinforcement learning with verifiable rewards have demonstrated not…

• Exemplars in Disguise: Pure Exemplar Models Mimic Abstraction-First Learning

  Zachary Nicholas Houghton, Vsevolod Kapatsinski · 4 August 2026

  Whether idiosyncratic, item-specific knowledge is learned before abstract class-level generalizations, or vice versa, is a central question in language learning, with exemplar and abstraction-based theories making opposite predictions. Recent methods have claimed to show that, at least for large lan…

• Cross-Task Dissociation in Frontier Vision-Language Model Theory of Mind

  Kejia Zhang, Youran Sun, Chugang Yi, Haizhao Yang · 4 August 2026

  Do frontier vision-language models present a coherent Theory-of-Mind (ToM) profile across tasks, matching the same human reference group, or does that profile fragment from one paradigm to the next? We evaluate a shared panel of nine frontier VLMs on two psychology-derived benchmarks: the Keysar Dir…

• What Can Latent World Models Know? Physical Parameter Identifiability in Multimodal Predictive Representations

  Kaizhen Tan (New York University, Carnegie Mellon University), Xin Xu (Carnegie Mellon University), Siru Tao (Carnegie Mellon University), Hanzhe Hong (Carnegie Mellon University), Yang Feng (Columbia University), Heqing Du (Columbia University) · 30 July 2026

  A central premise of latent world models is that predicting the future forces a representation to internalize the physics of its environment. Which physical quantities does a trained latent actually contain, and what decides this? We answer with controlled interventions in POKEWORLD, an interactive …

• Shared SFT Lessons Across Alignment, Model Organisms, and Toy Models

  Anton de la Fuente, Arthur Conmy · 30 July 2026

  Alignment training, model organisms, and toy models are usually treated as separate research areas. But projects in all three frequently use supervised fine-tuning (SFT) to pursue the same underlying goals. When projects share a goal, we should test whether lessons learned from one area transfer to …

• Differentiable Logic Programming to Mitigate Reasoning Shortcuts in Neurosymbolic Systems

  Akihiro Takemura (National Institute of Informatics, Tokyo, Japan), Katsumi Inoue (National Institute of Informatics, Tokyo, Japan) · 24 July 2026

  Neurosymbolic (NeSy) systems integrate neural networks with logical reasoning to achieve both generalization and interpretability, but recent work has shown they are susceptible to shortcut reasoning behaviors. We propose a novel method using matrix-based differentiable logic programming to mitigat…

• A computational model of infant sensorimotor exploration in the mobile paradigm

  Josua Spisak, Sergiu Tcaci Popescu, Stefan Wermter, Matej Hoffmann, J. Kevin O'Regan · 14 July 2026

  We present a computational model of the mechanisms that may determine infant behavior in the "mobile paradigm". This paradigm has been used in developmental psychology to explore how infants learn the sensory effects of their actions. In this paradigm, a mobile (an articulated and movable object han…

• Final Checkpoints Are Not Enough: Analyzing Latent Reasoning Faithfulness Along Training Trajectories

  Hengyu Jin, Shu Yang, Di Wang · 9 July 2026

  Latent reasoning methods perform multi-step inference entirely in the model's continuous hidden states, promising more compact and efficient reasoning. However, these opaque hidden states raise a question of faithfulness: whether these latent reasoning steps causally drive the final answer. Prior wo…

• Base Models Know How to Reason, Thinking Models Learn When

  Constantin Venhoff, Iv\'an Arcuschin, Philip Torr, Arthur Conmy, Neel Nanda · 8 July 2026

  What do thinking language models learn during training that their base models lack? We first present an unsupervised method that discovers a model's reasoning behaviors by training small Sparse Autoencoders on sentence-level activations of reasoning traces, yielding interpretable reasoning taxonomie…