{"total":18,"rows":[{"id":"2410.06833","title":"Dynamic metastability in the self-attention model","created":"2024-10-09","cited_by_count":46,"area":null},{"id":"2411.04551","title":"Measure-to-measure interpolation using Transformers","created":"2024-11-07","cited_by_count":29,"area":null},{"id":"2504.04308","title":"Gating is Weighting: Understanding Gated Linear Attention through In-context Learning","created":"2025-04-06","cited_by_count":12,"area":null},{"id":"2410.02247","title":"Theoretical Insights into Fine-Tuning Attention Mechanism: Generalization and Optimization","created":"2024-10-03","cited_by_count":9,"area":null},{"id":"2410.14581","title":"Optimizing Attention with Mirror Descent: Generalized Max-Margin Token Selection","created":"2024-10-18","cited_by_count":9,"area":null},{"id":"2402.15415","title":"Understanding Catastrophic Forgetting In LoRA via Mean-Field Attention Dynamics","created":"2024-02-23","cited_by_count":7,"area":null},{"id":"2410.13060","title":"AERO: Entropy-Guided Framework for Private LLM Inference","created":"2024-10-16","cited_by_count":3,"area":null},{"id":"2509.07324","title":"Mitigating Attention Localization in Small Scale: Self-Attention Refinement via One-step Belief Propagation","created":"2025-09-09","cited_by_count":3,"area":null},{"id":"2603.06922","title":"NerVE: Nonlinear Eigenspectrum Dynamics in LLM Feed-Forward Networks","created":"2026-03-06","cited_by_count":3,"area":null},{"id":"2603.06248","title":"Gradient Flow Polarizes Softmax Outputs towards Low-Entropy Solutions","created":"2026-03-06","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":"2507.09394","title":"A Random Matrix Theory Perspective on the Learning Dynamics of Multi-head Latent Attention","created":"2025-07-12","cited_by_count":1,"area":null},{"id":"2511.20698","title":"On the Role of Hidden States of Modern Hopfield Network in Transformer","created":"2025-11-24","cited_by_count":1,"area":null},{"id":"2604.00199","title":"QUEST: A robust attention formulation using query-modulated spherical attention","created":"2026-03-31","cited_by_count":1,"area":null},{"id":"2608.06776","title":"Faster Query-Key Learning Sharpens Attention in Self-Attention Models","created":"2026-08-07","cited_by_count":1,"area":null},{"id":"2602.01308","title":"Dispelling the Curse of Singularities in Neural Network Optimizations","created":"2026-02-01","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":"2609.34273","title":"Query Expansion and Key Specialization in Transformer Attention Geometry","created":"2026-09-28","cited_by_count":0,"area":null}],"next_cursor":null}