{"total":13,"rows":[{"id":"2406.04267","title":"Transformers need glasses! Information over-squashing in language tasks","created":"2024-06-06","cited_by_count":91,"area":null},{"id":"2410.01104","title":"Softmax is not Enough (for Sharp Size Generalisation)","created":"2024-10-01","cited_by_count":46,"area":null},{"id":"2402.15332","title":"Position: Categorical Deep Learning is an Algebraic Theory of All Architectures","created":"2024-02-23","cited_by_count":32,"area":null},{"id":"2507.12224","title":"Optimizers Qualitatively Alter Solutions And We Should Leverage This","created":"2025-07-16","cited_by_count":17,"area":null},{"id":"2406.05816","title":"Attention as a Hypernetwork","created":"2024-06-09","cited_by_count":13,"area":null},{"id":"2503.19173","title":"Graph neural networks extrapolate out-of-distribution for shortest paths","created":"2025-03-24","cited_by_count":11,"area":null},{"id":"2505.24067","title":"Primal-Dual Neural Algorithmic Reasoning","created":"2025-05-29","cited_by_count":9,"area":null},{"id":"2409.07154","title":"Recurrent Aggregators in Neural Algorithmic Reasoning","created":"2024-09-11","cited_by_count":6,"area":null},{"id":"2410.15059","title":"Deep Equilibrium Algorithmic Reasoning","created":"2024-10-19","cited_by_count":6,"area":null},{"id":"2407.00494","title":"Graph Neural Networks Gone Hogwild","created":"2024-06-29","cited_by_count":2,"area":null},{"id":"2506.05814","title":"Positional Encoding meets Persistent Homology on Graphs","created":"2025-06-06","cited_by_count":1,"area":null},{"id":"2510.16289","title":"Disentangling Hyperedges through the Lens of Category Theory","created":"2025-10-18","cited_by_count":0,"area":null},{"id":"2605.20074","title":"Towards Distillation Guarantees under Algorithmic Alignment for Combinatorial Optimization","created":"2026-05-19","cited_by_count":0,"area":null}],"next_cursor":null}