{"total":33,"rows":[{"id":"2410.06833","title":"Dynamic metastability in the self-attention model","created":"2024-10-09","cited_by_count":46,"area":null},{"id":"2502.10818","title":"On Vanishing Gradients, Over-Smoothing, and Over-Squashing in GNNs: Bridging Recurrent and Graph Learning","created":"2025-02-15","cited_by_count":43,"area":null},{"id":"2411.04551","title":"Measure-to-measure interpolation using Transformers","created":"2024-11-07","cited_by_count":29,"area":null},{"id":"2511.11553","title":"Multistability of Self-Attention Dynamics in Transformers","created":"2025-11-14","cited_by_count":8,"area":null},{"id":"2501.00762","title":"Residual connections provably mitigate oversmoothing in graph neural networks","created":"2025-01-01","cited_by_count":7,"area":null},{"id":"2510.17457","title":"Deeper with Riemannian Geometry: Overcoming Oversmoothing and Oversquashing for Graph Foundation Models","created":"2025-10-20","cited_by_count":7,"area":null},{"id":"2409.11504","title":"Preventing Representational Rank Collapse in MPNNs by Splitting the Computational Graph","created":"2024-09-17","cited_by_count":6,"area":null},{"id":"2502.04591","title":"Are We Measuring Oversmoothing in Graph Neural Networks Correctly?","created":"2025-02-07","cited_by_count":6,"area":null},{"id":"2506.05249","title":"On the Convergence of Gradient Descent on Learning Transformers with Residual Connections","created":"2025-06-05","cited_by_count":6,"area":null},{"id":"2603.05395","title":"On the Necessity of Learnable Sheaf Laplacians","created":"2026-03-05","cited_by_count":5,"area":null},{"id":"2407.11876","title":"Simplifying the Theory on Over-Smoothing","created":"2024-07-16","cited_by_count":4,"area":null},{"id":"2502.11394","title":"A Signed Graph Approach to Understanding and Mitigating Oversmoothing in GNNs","created":"2025-02-17","cited_by_count":2,"area":null},{"id":"2505.18088","title":"Early-Exit Graph Neural Networks","created":"2025-05-23","cited_by_count":2,"area":null},{"id":"2601.07419","title":"Position: Don't be Afraid of Over-Smoothing And Over-Squashing","created":"2026-01-12","cited_by_count":2,"area":null},{"id":"2602.15634","title":"Beyond ReLU: Bifurcation, Oversmoothing, and Topological Priors","created":"2026-02-17","cited_by_count":2,"area":null},{"id":"2606.23364","title":"Convergence of Gradient Descent for General Neural Network Architectures Beyond the NTK Regime","created":"2026-06-22","cited_by_count":2,"area":null},{"id":"2506.24120","title":"Data Uniformity Improves Training Efficiency and More, with a Convergence Framework Beyond the NTK Regime","created":"2025-06-30","cited_by_count":1,"area":null},{"id":"2508.03111","title":"GEDAN: Learning the Edit Costs for Graph Edit Distance","created":"2025-08-05","cited_by_count":1,"area":null},{"id":"2509.19084","title":"Bridging Computational Social Science and Deep Learning: Cultural Dissemination-Inspired Graph Neural Networks","created":"2025-09-23","cited_by_count":0,"area":null},{"id":"2510.17378","title":"Model Metamers Reveal Invariances in Graph Neural Networks","created":"2025-10-20","cited_by_count":0,"area":null},{"id":"2512.08475","title":"Solving Oversmoothing in GNNs via Nonlocal Message Passing: Algebraic Smoothing and Depth Scalability","created":"2025-12-09","cited_by_count":0,"area":null},{"id":"2512.11901","title":"CLARGA: Multimodal Graph Representation Learning over Arbitrary Sets of Modalities","created":"2025-12-10","cited_by_count":0,"area":null},{"id":"2512.14619","title":"ParaFormer: A Generalized PageRank Graph Transformer for Graph Representation Learning","created":"2025-12-16","cited_by_count":0,"area":null},{"id":"2602.10031","title":"Graph Learning Should Move Beyond Restrictive Views of Spectral and Message-Passing GNNs","created":"2026-02-10","cited_by_count":0,"area":null},{"id":"2603.08825","title":"Local Message-Passing for Discrete Graph Generation","created":"2026-03-09","cited_by_count":0,"area":null},{"id":"2605.15723","title":"GOMA: Toward Structure-Driven Multimodal Alignment from a Graph Signal Smoothing Perspective","created":"2026-05-15","cited_by_count":0,"area":null},{"id":"2605.25619","title":"Analogies between Transformer Layers and Power Method","created":"2026-05-25","cited_by_count":0,"area":null},{"id":"2606.22895","title":"Learning Graphs through Continuous Information Entropy Fields","created":"2026-06-22","cited_by_count":0,"area":null},{"id":"2606.23572","title":"A Spectral Theory of Normalized Corrected GNN Propagation","created":"2026-06-22","cited_by_count":0,"area":null},{"id":"2608.12514","title":"Exploring Oversmoothing with Householder Matrices","created":"2026-08-12","cited_by_count":0,"area":null},{"id":"2609.13920","title":"Finite-Time Node Separation in Recurrent Graph Neural Networks with Persistent Gaussian Perturbations","created":"2026-09-12","cited_by_count":0,"area":null},{"id":"2610.03556","title":"Get a GRIP, this will be a long TRIP: A Quantifiable Long-Range Framework for Verifying Over-squashing","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.13518","title":"Asymptotic Analysis of Discrete-Time Self-Attention Dynamics in Transformers","created":"2026-10-09","cited_by_count":0,"area":null}],"next_cursor":null}