{"total":23,"rows":[{"id":"2505.21829","title":"In Search of Adam's Secret Sauce","created":"2025-05-27","cited_by_count":40,"area":null},{"id":"2505.16130","title":"Generative Graph Pattern Machine","created":"2025-05-22","cited_by_count":11,"area":null},{"id":"2411.19455","title":"Autocorrelation Matters: Understanding the Role of Initialization Schemes for State Space Models","created":"2024-11-29","cited_by_count":9,"area":null},{"id":"2605.20613","title":"HRM-Text: Efficient Pretraining Beyond Scaling","created":"2026-05-20","cited_by_count":9,"area":null},{"id":"2508.19029","title":"Revisiting associative recall in modern recurrent models","created":"2025-08-26","cited_by_count":8,"area":null},{"id":"2508.16817","title":"Predictability Enables Parallelization of Nonlinear State Space Models","created":"2025-08-22","cited_by_count":7,"area":null},{"id":"2411.04760","title":"Zero-Shot Temporal Resolution Domain Adaptation for Spiking Neural Networks","created":"2024-11-07","cited_by_count":6,"area":null},{"id":"2408.08055","title":"DeNOTS: Stable Deep Neural ODEs for Time Series","created":"2024-08-15","cited_by_count":5,"area":null},{"id":"2506.01153","title":"Weight-Space Linear Recurrent Neural Networks","created":"2025-06-01","cited_by_count":5,"area":null},{"id":"2505.19827","title":"Revisiting Glorot Initialization for Long-Range Linear Recurrences","created":"2025-05-26","cited_by_count":2,"area":null},{"id":"2508.12121","title":"Time-Scale Coupling Between States and Parameters in Recurrent Neural Networks","created":"2025-08-16","cited_by_count":2,"area":null},{"id":"2510.09389","title":"Design Principles for Sequence Models via Coefficient Dynamics","created":"2025-10-10","cited_by_count":1,"area":null},{"id":"2601.12598","title":"Dissecting Linear Recurrent Models: How Different Gating Strategies Drive Selectivity and Generalization","created":"2026-01-18","cited_by_count":1,"area":null},{"id":"2602.10911","title":"Tuning the burn-in phase in training recurrent neural networks improves their performance","created":"2026-02-11","cited_by_count":1,"area":null},{"id":"2606.14259","title":"Beyond a Single Explanation of the Adam--SGD Gap","created":"2026-06-12","cited_by_count":1,"area":null},{"id":"2506.12810","title":"Lyapunov Learning at the Onset of Chaos","created":"2025-06-15","cited_by_count":0,"area":null},{"id":"2508.11166","title":"Overcoming Low-Resource Barriers in Tulu: Neural Models and Corpus Creation for OffensiveLanguage Identification","created":"2025-08-15","cited_by_count":0,"area":null},{"id":"2509.03677","title":"Insights from Gradient Dynamics: Gradient Autoscaled Normalization","created":"2025-09-03","cited_by_count":0,"area":null},{"id":"2602.12021","title":"Improved state mixing in higher-order and block diagonal linear recurrent networks","created":"2026-02-12","cited_by_count":0,"area":null},{"id":"2603.19198","title":"Extending SSMs with the Exponentially Weighted Signature","created":"2026-03-19","cited_by_count":0,"area":null},{"id":"2603.23076","title":"MsFormer: Enabling Robust Predictive Maintenance Services for Industrial Devices","created":"2026-03-24","cited_by_count":0,"area":null},{"id":"2605.12683","title":"Parallel-in-Time Training of Recurrent Neural Networks for Dynamical Systems Reconstruction","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2606.00243","title":"Dynamics and Representation Structure of Local Approximations to Gradient-Based Learning in Linear Recurrent Neural Networks","created":"2026-05-29","cited_by_count":0,"area":null}],"next_cursor":null}