{"total":24,"rows":[{"id":"2606.02993","title":"Neural Networks Provably Learn Spectral Representations for Group Composition","created":"2026-06-02","cited_by_count":3,"area":null},{"id":"2605.20441","title":"Weight Decay Regimes in Grokking Transformers: Cheap Online Diagnostics","created":"2026-05-19","cited_by_count":2,"area":null},{"id":"2607.10039","title":"Are We Ready for AI-Driven Discovery? AI Verification Before the Next Fundamental Physics Breakthrough","created":"2026-07-10","cited_by_count":2,"area":null},{"id":"2608.15448","title":"Language models suffer from a curse of ambiguity","created":"2026-08-15","cited_by_count":2,"area":null},{"id":"2605.13370","title":"Phasor Memory Networks: Stable Backpropagation Through Time for Scalable Explicit Memory","created":"2026-05-13","cited_by_count":1,"area":null},{"id":"2604.24037","title":"A Limit Theory of Foundation Models: A Mathematical Approach to Understanding Emergent Intelligence and Scaling Laws","created":"2026-04-27","cited_by_count":0,"area":null},{"id":"2605.09031","title":"Spherical Boltzmann machines: a solvable theory of learning and generation in energy-based models","created":"2026-05-09","cited_by_count":0,"area":null},{"id":"2605.10655","title":"BCJR-QAT: A Differentiable Relaxation of Trellis-Coded Weight Quantization","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2605.12763","title":"Center-Manifold Reduction of Learning at Bifurcations: Interference and Rich Learning in Recurrent Neural Networks","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2605.21692","title":"Representation Gap: Explaining the Unreasonable Effectiveness of Neural Networks from a Geometric Perspective","created":"2026-05-20","cited_by_count":0,"area":null},{"id":"2606.00073","title":"Rare Events, Real Signals: Functional Ensembles as Units of Computation in Deep Spiking Networks","created":"2026-05-21","cited_by_count":0,"area":null},{"id":"2606.05335","title":"A prism hierarchy of learning regimes in large linear autoencoders","created":"2026-06-03","cited_by_count":0,"area":null},{"id":"2606.20347","title":"Critical Percolation as a Synthetic Data Model for Interpretability","created":"2026-06-18","cited_by_count":0,"area":null},{"id":"2606.29519","title":"Anti-Collapse Dynamics and the Emergence of Multi-Time-Scale Learning in Recurrent Neural Networks","created":"2026-06-28","cited_by_count":0,"area":null},{"id":"2607.03634","title":"The Role of Rigor in Artificial Intelligence","created":"2026-05-19","cited_by_count":0,"area":null},{"id":"2607.07035","title":"On the Principles of Deep Feedforward ReLU Networks","created":"2026-07-08","cited_by_count":0,"area":null},{"id":"2607.19195","title":"Free energy landscape of Dense Associative Memory","created":"2026-07-21","cited_by_count":0,"area":null},{"id":"2608.06597","title":"Cascading Through the Hierarchy: Regularizer-Induced Feature Detection as Phase Transitions in Deep Linear Neural Networks","created":"2026-08-06","cited_by_count":0,"area":null},{"id":"2608.08350","title":"Correlation flow governs learning at criticality","created":"2026-08-08","cited_by_count":0,"area":null},{"id":"2608.19331","title":"Deep neural networks as lattice gauge theories","created":"2026-08-19","cited_by_count":0,"area":null},{"id":"2608.30946","title":"Reproducible macroscopic dynamics in a closed-loop human-AI learning system","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.13057","title":"Benign Loss Landscapes Can Coexist with Worst-Case Hardness","created":"2026-09-11","cited_by_count":0,"area":null},{"id":"2609.19924","title":"The Life of a Token: from Words to Bits on the Wire","created":"2026-09-17","cited_by_count":0,"area":null},{"id":"2609.31384","title":"Multivariate conformal uncertainty propagation in multitask atomistic simulation: Successes and pitfalls","created":"2026-09-25","cited_by_count":0,"area":null}],"next_cursor":null}