{"total":29,"rows":[{"id":"2602.11534","title":"Krause Synchronization Transformers","created":"2026-02-12","cited_by_count":5,"area":null},{"id":"2605.10931","title":"Quantifying Concentration Phenomena of Mean-Field Transformers in the Low-Temperature Regime","created":"2026-05-11","cited_by_count":5,"area":null},{"id":"2603.06187","title":"Random Quadratic Form on a Sphere: Synchronization by Common Noise","created":"2026-03-06","cited_by_count":4,"area":null},{"id":"2605.16747","title":"Propagation of Chaos in Contextual Flow Maps","created":"2026-05-16","cited_by_count":3,"area":null},{"id":"2607.18584","title":"On the Diverse Dynamical Behaviors Arising in Deep Linear Transformers","created":"2026-07-20","cited_by_count":3,"area":null},{"id":"2601.23236","title":"YuriiFormer: A Suite of Nesterov-Accelerated Transformers","created":"2026-01-30","cited_by_count":2,"area":null},{"id":"2605.04279","title":"Gradient Flow Structure and Quantitative Dynamics of Multi-Head Self-Attention","created":"2026-05-05","cited_by_count":2,"area":null},{"id":"2605.23778","title":"The physics of AI weather models","created":"2026-05-22","cited_by_count":2,"area":null},{"id":"2602.20624","title":"Physics-based phenomenological characterization of cross-modal bias in multimodal models","created":"2026-02-24","cited_by_count":1,"area":null},{"id":"2603.26940","title":"Static and Dynamic Approaches to Computing Barycenters of Probability Measures on Graphs","created":"2026-03-27","cited_by_count":1,"area":null},{"id":"2605.01107","title":"Diffusion Operator Geometry of Feedforward Representations","created":"2026-05-01","cited_by_count":1,"area":null},{"id":"2605.07772","title":"Training-Induced Escape from Token Clustering in a Mean-Field Formulation of Transformers","created":"2026-05-08","cited_by_count":1,"area":null},{"id":"2605.21365","title":"$L^2$ over Wasserstein: Statistical Analysis for Optimal Transport","created":"2026-05-20","cited_by_count":1,"area":null},{"id":"2608.08922","title":"Clustered Attractor Manifolds and Dynamical Condensation in Self-Attention","created":"2026-08-09","cited_by_count":1,"area":null},{"id":"2609.35483","title":"Universal Approximation of Measure-to-Measure Operators by Pushforwards","created":"2026-09-28","cited_by_count":1,"area":null},{"id":"2604.11613","title":"Symmetry Reveals Layerwise Dynamics: How Transformers Perform In-Context Classification","created":"2026-04-13","cited_by_count":0,"area":null},{"id":"2604.22580","title":"Explanation of Dynamic Physical Field Predictions using WassersteinGrad: Application to Autoregressive Weather Forecasting","created":"2026-04-24","cited_by_count":0,"area":null},{"id":"2605.11059","title":"Uniform Scaling Limits in AdamW-Trained Transformers","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2605.12697","title":"A Unified Framework for Critical Scaling of Inverse Temperature in Self-Attention","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2605.29351","title":"Attention as In-Context Empirical Bayes: A Two-Stage View via Particle Dynamics","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2605.30229","title":"Anti Mode-Collapse in Mean-Field Transformer via Auxiliary Variables","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2607.24502","title":"Self-Attention Dynamics with Rotary Position Embeddings: Twisted States and Explicit Consensus Rates on the Sphere","created":"2026-07-27","cited_by_count":0,"area":null},{"id":"2607.25279","title":"Many-body Tipping Dynamics of ChatGPT-like AIs","created":"2026-07-28","cited_by_count":0,"area":null},{"id":"2608.16664","title":"Random Quadratic Form with random forcing: Metastable synchronization by noise","created":"2026-08-17","cited_by_count":0,"area":null},{"id":"2609.24202","title":"Opinion Leader Dynamics: How Sparse Attention Shapes Token Clustering","created":"2026-09-21","cited_by_count":0,"area":null},{"id":"2609.27008","title":"Sharp Convergence of Wasserstein Gradient Flows for Spectrally Nonnegative Interaction Energies","created":"2026-09-22","cited_by_count":0,"area":null},{"id":"2609.33016","title":"Relative Generalization Invariance of LLM Pretraining","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2610.04493","title":"Understanding Clustering in Slot Attention via Particle Dynamics","created":"2026-10-03","cited_by_count":0,"area":null},{"id":"2610.19358","title":"Asymptotic Behavior of Transformers","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}