{"total":52,"rows":[{"id":"2605.18855","title":"Delta Attention Residuals","created":"2026-05-13","cited_by_count":7,"area":null},{"id":"2606.25008","title":"Neural Scaling Universality: If Exponents Are Fixed, Time to Understand Coefficients","created":"2026-06-23","cited_by_count":5,"area":null},{"id":"2605.25704","title":"PowLU: An Activation Function for Stable Pre-Training of LLMs","created":"2026-05-25","cited_by_count":4,"area":null},{"id":"2603.16039","title":"Residual Stream Duality in Modern Transformer Architectures","created":"2026-03-17","cited_by_count":3,"area":null},{"id":"2604.03955","title":"Symbolic-Vector Attention Fusion for Collective Intelligence","created":"2026-04-05","cited_by_count":3,"area":null},{"id":"2605.17887","title":"Attention Sinks and Outliers in Attention Residuals","created":"2026-05-18","cited_by_count":2,"area":null},{"id":"2606.28116","title":"Mechanism-Driven Monitors for Preemptive Detection of LLM Training Instability","created":"2026-06-26","cited_by_count":2,"area":null},{"id":"2607.10664","title":"Edge Cluster Expansion with Radial Rotary Attention for Interatomic Potentials","created":"2026-07-12","cited_by_count":2,"area":null},{"id":"2607.27230","title":"Multi-Head Attention Residuals","created":"2026-07-22","cited_by_count":2,"area":null},{"id":"2608.20334","title":"Exploring the Performance Frontier of Compact Unified Image Generation Models","created":"2026-08-20","cited_by_count":2,"area":null},{"id":"2609.19107","title":"How Model Growth, Recursion, and Boundary Operators Influence Scaling Exponents","created":"2026-09-16","cited_by_count":2,"area":null},{"id":"2605.03953","title":"Transformers with Selective Access to Early Representations","created":"2026-05-05","cited_by_count":1,"area":null},{"id":"2605.09850","title":"Probing Routing-Conditional Calibration in Attention-Residual Transformers","created":"2026-05-11","cited_by_count":1,"area":null},{"id":"2605.23259","title":"Multi-Gate Residuals","created":"2026-05-22","cited_by_count":1,"area":null},{"id":"2607.07953","title":"Linear Attention Architectures: Mechanisms, Trade-offs, and Cross-Layer Routing","created":"2026-07-08","cited_by_count":1,"area":null},{"id":"2609.32534","title":"DepthBench: Measuring How Residual Connections Enable More Computational Depth","created":"2026-09-26","cited_by_count":1,"area":null},{"id":"2603.28507","title":"Continued AI Scaling Requires Repeated Efficiency Doublings","created":"2026-03-30","cited_by_count":0,"area":null},{"id":"2604.03190","title":"Gradient Boosting within a Single Attention Layer","created":"2026-04-03","cited_by_count":0,"area":null},{"id":"2604.03297","title":"XAttnRes: Cross-Stage Attention Residuals for Medical Image Segmentation","created":"2026-03-28","cited_by_count":0,"area":null},{"id":"2604.04250","title":"CAWN: Continuous Acoustic Wave Networks for Autoregressive Language Modeling","created":"2026-04-05","cited_by_count":0,"area":null},{"id":"2604.15593","title":"DALM: A Domain-Algebraic Language Model via Three-Phase Structured Generation","created":"2026-04-17","cited_by_count":0,"area":null},{"id":"2605.01376","title":"A Cellular Doctrine of Morality: Intrinsic Active Precision and the Mind-Reality Overload Dilemma","created":"2026-05-02","cited_by_count":0,"area":null},{"id":"2605.06317","title":"NavOne: One-Step Global Planning for Vision-Language Navigation on Top-Down Maps","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2605.06501","title":"Cubit: Token Mixer with Kernel Ridge Regression","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2605.08423","title":"Queryable LoRA: Instruction-Regularized Routing Over Shared Low-Rank Update Atoms","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2605.08806","title":"L2A: Learning to Accumulate Pose History for Accurate 3D Human Pose Estimation","created":"2026-05-09","cited_by_count":0,"area":null},{"id":"2605.25518","title":"Cross-Stage Attention Multi-Expert Network for Radiologist-Inspired Breast Ultrasound Diagnosis","created":"2026-05-25","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":"2606.04445","title":"RowNet: A Memory Transformer for Tabular Regression","created":"2026-06-03","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":"2606.22325","title":"All Routes Lead to Collapse","created":"2026-06-21","cited_by_count":0,"area":null},{"id":"2606.31859","title":"Review Residuals: Update-Conditioned Residual Gating for Transformers","created":"2026-06-30","cited_by_count":0,"area":null},{"id":"2607.08545","title":"Structural Bottlenecks on Frequency Representation in End-to-End Audio Models","created":"2026-07-09","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":"2608.14290","title":"Intern-S2-Mobius: Foundation Model with Decoupled Knowledge and Reasoning","created":"2026-08-14","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":"2608.25243","title":"From Memorization to Absorption: Mixed-Policy RL for Continual Knowledge Injection","created":"2026-08-26","cited_by_count":0,"area":null},{"id":"2609.08574","title":"Do New Attention Mechanisms Actually Fix Attention Sinks at Million-Token Context?","created":"2026-09-08","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":"2609.17886","title":"Dataset-Dependent Effects of Cross-Depth Aggregation and Soft-Routed Experts in EEG Foundation Model Fine-Tuning","created":"2026-09-15","cited_by_count":0,"area":null},{"id":"2609.19521","title":"Storing Is Not Remembering: LSTM-UT and Bounded Gated Memory for Looped Transformers","created":"2026-09-17","cited_by_count":0,"area":null},{"id":"2609.28006","title":"Shared Global KV with Layer-Specific Local History","created":"2026-09-23","cited_by_count":0,"area":null},{"id":"2609.32457","title":"Write Back the $\\Delta$: Revisiting the Same Tokens with Fresh Representations","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.36971","title":"Structured Visual Target Learning For Cross-Subject eeg-to-image retrieval","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.38956","title":"Routing Probes Can Improve Without New Information: An Exact-Null Audit of Uncertainty Beyond Model Outputs","created":"2026-09-30","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":"2609.39661","title":"The Evolution of Attention in Large Language Models: Mechanisms, Trade-offs, and Emerging Trends","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.01495","title":"Auditing Routing Entropy as an Uncertainty Signal in Attention-Residual Transformers","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.02144","title":"Faynt: Scaling and Optimizing Policies for Competitive Melee","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.09179","title":"LayerRoPE: Dynamic Depth-wise Magnitude & Angular Superposition","created":"2026-10-06","cited_by_count":0,"area":null},{"id":"2610.11570","title":"Scaling to Tens of Thousands of Test-Time Iterations with Loop-Native Attention Residuals","created":"2026-10-08","cited_by_count":0,"area":null},{"id":"2610.13630","title":"Multi-Stream Attention Residuals","created":"2026-10-09","cited_by_count":0,"area":null}],"next_cursor":null}