{"total":28,"rows":[{"id":"2512.24880","title":"mHC: Manifold-Constrained Hyper-Connections","created":"2025-12-31","cited_by_count":88,"area":null},{"id":"2603.15031","title":"Attention Residuals","created":"2026-03-16","cited_by_count":65,"area":null},{"id":"2604.21254","title":"Hyperloop Transformers","created":"2026-04-23","cited_by_count":12,"area":null},{"id":"2601.21579","title":"KromHC: Manifold-Constrained Hyper-Connections with Kronecker-Product Residual Matrices","created":"2026-01-29","cited_by_count":11,"area":null},{"id":"2601.00417","title":"Deep Delta Learning","created":"2026-01-01","cited_by_count":9,"area":null},{"id":"2510.07739","title":"MeSH: Memory-as-State-Highways for Recursive Transformers","created":"2025-10-09","cited_by_count":8,"area":null},{"id":"2605.18855","title":"Delta Attention Residuals","created":"2026-05-13","cited_by_count":7,"area":null},{"id":"2503.06473","title":"Enhancing Layer Attention Efficiency through Pruning Redundant Retrievals","created":"2025-03-09","cited_by_count":3,"area":null},{"id":"2511.11238","title":"Virtual Width Networks","created":"2025-11-14","cited_by_count":3,"area":null},{"id":"2603.16039","title":"Residual Stream Duality in Modern Transformer Architectures","created":"2026-03-17","cited_by_count":3,"area":null},{"id":"2607.27230","title":"Multi-Head Attention Residuals","created":"2026-07-22","cited_by_count":2,"area":null},{"id":"2603.22665","title":"Improving LLM Final Representations with Inter-Layer Geometry","created":"2026-03-24","cited_by_count":1,"area":null},{"id":"2605.03953","title":"Transformers with Selective Access to Early Representations","created":"2026-05-05","cited_by_count":1,"area":null},{"id":"2607.09694","title":"Low-Rank Attention Residuals","created":"2026-06-19","cited_by_count":1,"area":null},{"id":"2607.18730","title":"Dual Attention Residuals","created":"2026-07-21","cited_by_count":1,"area":null},{"id":"2601.08131","title":"Attention Projection Mixing with Exogenous Anchors","created":"2026-01-13","cited_by_count":0,"area":null},{"id":"2606.06564","title":"HAARES Half-Split Residual Basis Routing for Deep Transformers","created":"2026-06-04","cited_by_count":0,"area":null},{"id":"2606.28405","title":"Enhancing Layer Interaction Using Key-Correlated Layer Attention","created":"2026-06-24","cited_by_count":0,"area":null},{"id":"2607.26192","title":"Dynamic Parameterization Is Not Dynamic Inference","created":"2026-07-28","cited_by_count":0,"area":null},{"id":"2608.01075","title":"Role-Decoupled Attention Residuals: Separating Matching and Content Retrieval Across Depth","created":"2026-08-02","cited_by_count":0,"area":null},{"id":"2608.18486","title":"WhiteMatter: All-to-All Cross-Layer Connections via KV Source Mixing","created":"2026-08-19","cited_by_count":0,"area":null},{"id":"2609.10715","title":"NCP-ArchPreview Technical Report: Moving towards Latent Space Language Models through Next Concept Prediction","created":"2026-09-09","cited_by_count":0,"area":null},{"id":"2609.27523","title":"M3D-Net: Hierarchical Coordination of Spatial Context, Feature Reuse, and Differential Attention for Mammography Classification","created":"2026-09-23","cited_by_count":0,"area":null},{"id":"2609.39109","title":"T-Router: Learning Thalamic Routing for Reasoning with Parameter-Efficient Reinforcement Learning","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.06653","title":"The Birkhoff Geometry of Manifold-Constrained Hyper-Connections: Two Channels, Vertex Viscosity, and Sinkhorn as a Retraction","created":"2026-10-05","cited_by_count":0,"area":null},{"id":"2610.13630","title":"Multi-Stream Attention Residuals","created":"2026-10-09","cited_by_count":0,"area":null},{"id":"2610.18809","title":"Depth Memory","created":"2026-10-13","cited_by_count":0,"area":null},{"id":"2610.19625","title":"DAGFormer: Global Topology Prediction for Transformer Cross-Layer Connections","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}