{"total":22,"rows":[{"id":"2604.21691","title":"There Will Be a Scientific Theory of Deep Learning","created":"2026-04-23","cited_by_count":29,"area":null},{"id":"2402.04875","title":"On Provable Length and Compositional Generalization","created":"2024-02-07","cited_by_count":22,"area":null},{"id":"2405.16391","title":"When does compositional structure yield compositional generalization? A kernel theory","created":"2024-05-26","cited_by_count":20,"area":null},{"id":"2406.05816","title":"Attention as a Hypernetwork","created":"2024-06-09","cited_by_count":13,"area":null},{"id":"2410.06303","title":"Compositional Risk Minimization","created":"2024-10-08","cited_by_count":13,"area":null},{"id":"2410.14817","title":"A Complexity-Based Theory of Compositionality","created":"2024-10-18","cited_by_count":13,"area":null},{"id":"2506.09272","title":"G-Sim: Generative Simulations with Large Language Models and Gradient-Free Calibration","created":"2025-06-10","cited_by_count":8,"area":null},{"id":"2407.12275","title":"When can transformers compositionally generalize in-context?","created":"2024-07-17","cited_by_count":7,"area":null},{"id":"2507.07207","title":"Scaling can lead to compositional generalization","created":"2025-07-09","cited_by_count":7,"area":null},{"id":"2410.06232","title":"Range, not Independence, Drives Modularity in Biologically Inspired Representations","created":"2024-10-08","cited_by_count":4,"area":null},{"id":"2603.14483","title":"Disentangling Dynamical Systems: Causal Representation Learning Meets Local Sparse Attention","created":"2026-03-15","cited_by_count":3,"area":null},{"id":"2411.03840","title":"Flexible task abstractions emerge in linear networks with fast and bounded units","created":"2024-11-06","cited_by_count":2,"area":null},{"id":"2507.11688","title":"Composing Linear Layers from Irreducibles","created":"2025-07-15","cited_by_count":2,"area":null},{"id":"2603.14147","title":"An Alternative Trajectory for Generative AI","created":"2026-03-14","cited_by_count":1,"area":null},{"id":"2406.17714","title":"Compositional Models for Estimating Causal Effects","created":"2024-06-25","cited_by_count":0,"area":null},{"id":"2505.02627","title":"A Theoretical Analysis of Provable Compositional Generalization in Neural Networks: A Necessary and Sufficient Condition","created":"2025-05-05","cited_by_count":0,"area":null},{"id":"2604.23903","title":"Integrative neurocybernetic modeling in the era of large-scale neuroscience","created":"2026-04-26","cited_by_count":0,"area":null},{"id":"2605.22972","title":"A mathematical theory of balancing relational generalization and memorization","created":"2026-05-21","cited_by_count":0,"area":null},{"id":"2608.15971","title":"The Limits of Binding in Dual Encoders","created":"2026-08-16","cited_by_count":0,"area":null},{"id":"2608.16930","title":"EMAN: Optimization-Driven Capacity Growth through Path Emergence in Multi-Task Learning","created":"2026-08-05","cited_by_count":0,"area":null},{"id":"2609.33708","title":"A Spectral Theory of Compositional Learning","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2610.15081","title":"Knowledge transfer between simple discrete worlds","created":"2026-10-10","cited_by_count":0,"area":null}],"next_cursor":null}