{"total":39,"rows":[{"id":"2310.01082","title":"Linear attention is (maybe) all you need (to understand transformer optimization)","created":"2023-10-02","cited_by_count":98,"area":null},{"id":"2308.16898","title":"Transformers as Support Vector Machines","created":"2023-08-31","cited_by_count":74,"area":null},{"id":"2306.13596","title":"Max-Margin Token Selection in Attention Mechanism","created":"2023-06-23","cited_by_count":58,"area":null},{"id":"2310.00535","title":"JoMA: Demystifying Multilayer Transformers via JOint Dynamics of MLP and Attention","created":"2023-10-01","cited_by_count":52,"area":null},{"id":"2307.11353","title":"What can a Single Attention Layer Learn? A Study Through the Random Features Lens","created":"2023-07-21","cited_by_count":40,"area":null},{"id":"2402.04161","title":"Attention with Markov: A Framework for Principled Analysis of Transformers via Markov Chains","created":"2024-02-06","cited_by_count":40,"area":null},{"id":"2310.12680","title":"On the Optimization and Generalization of Multi-head Attention","created":"2023-10-19","cited_by_count":37,"area":null},{"id":"2402.15607","title":"How Do Nonlinear Transformers Learn and Generalize in In-Context Learning?","created":"2024-02-23","cited_by_count":35,"area":null},{"id":"2402.13512","title":"From Self-Attention to Markov Models: Unveiling the Dynamics of Generative Transformers","created":"2024-02-21","cited_by_count":34,"area":null},{"id":"2403.08081","title":"Mechanics of Next Token Prediction with Self-Attention","created":"2024-03-12","cited_by_count":34,"area":null},{"id":"2401.12902","title":"Facing the Elephant in the Room: Visual Prompt Tuning or Full Finetuning?","created":"2024-01-23","cited_by_count":31,"area":null},{"id":"2402.05738","title":"Implicit Bias and Fast Convergence Rates for Self-attention","created":"2024-02-08","cited_by_count":31,"area":null},{"id":"2407.17686","title":"Transformers on Markov Data: Constant Depth Suffices","created":"2024-07-25","cited_by_count":27,"area":null},{"id":"2402.04084","title":"Provably learning a multi-head attention layer","created":"2024-02-06","cited_by_count":21,"area":null},{"id":"2403.08699","title":"Implicit Regularization of Gradient Flow on One-Layer Softmax Attention","created":"2024-03-13","cited_by_count":19,"area":null},{"id":"2401.17426","title":"Superiority of Multi-Head Attention in In-Context Linear Regression","created":"2024-01-30","cited_by_count":17,"area":null},{"id":"2402.18551","title":"Implicit Optimization Bias of Next-Token Prediction in Linear Models","created":"2024-02-28","cited_by_count":14,"area":null},{"id":"2406.01977","title":"What Improves the Generalization of Graph Transformers? A Theoretical Dive into the Self-attention and Positional Encoding","created":"2024-06-04","cited_by_count":14,"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":"2410.14581","title":"Optimizing Attention with Mirror Descent: Generalized Max-Margin Token Selection","created":"2024-10-18","cited_by_count":9,"area":null},{"id":"2406.17167","title":"Learning on Transformers is Provable Low-Rank and Sparse: A One-layer Analysis","created":"2024-06-24","cited_by_count":8,"area":null},{"id":"2510.16670","title":"All You Need is One: Capsule Prompt Tuning with a Single Vector","created":"2025-10-19","cited_by_count":8,"area":null},{"id":"2407.05591","title":"On the Power of Convolution Augmented Transformer","created":"2024-07-08","cited_by_count":6,"area":null},{"id":"2512.18634","title":"From Shortcut to Induction Head: How Data Diversity Shapes Algorithm Selection in Transformers","created":"2025-12-21","cited_by_count":6,"area":null},{"id":"2402.02969","title":"Towards Understanding the Word Sensitivity of Attention Layers: A Study via Random Features","created":"2024-02-05","cited_by_count":5,"area":null},{"id":"2410.10101","title":"Learning Linear Attention in Polynomial Time","created":"2024-10-14","cited_by_count":5,"area":null},{"id":"2509.00421","title":"Memory Limitations of Prompt Tuning in Transformers","created":"2025-08-30","cited_by_count":4,"area":null},{"id":"2510.17526","title":"How Does Label Noise Gradient Descent Improve Generalization in the Low SNR Regime?","created":"2025-10-20","cited_by_count":4,"area":null},{"id":"2602.04872","title":"Multi-layer Cross-attention is Provably Optimal for Multi-modal In-context Learning","created":"2026-02-04","cited_by_count":2,"area":null},{"id":"2505.17282","title":"Attention with Trained Embeddings Provably Selects Important Tokens","created":"2025-05-22","cited_by_count":1,"area":null},{"id":"2506.16196","title":"Efficient and Privacy-Preserving Soft Prompt Transfer for LLMs","created":"2025-06-19","cited_by_count":1,"area":null},{"id":"2508.07878","title":"TAP: Parameter-efficient Task-Aware Prompting for Adverse Weather Removal","created":"2025-08-11","cited_by_count":1,"area":null},{"id":"2510.16446","title":"VIPAMIN: Visual Prompt Initialization via Embedding Selection and Subspace Expansion","created":"2025-10-18","cited_by_count":1,"area":null},{"id":"2601.16514","title":"Finite-Time Analysis of Gradient Descent for Shallow Transformers","created":"2026-01-23","cited_by_count":1,"area":null},{"id":"2604.06440","title":"Visual prompting reimagined: The power of the Activation Prompts","created":"2026-04-07","cited_by_count":1,"area":null},{"id":"2605.15787","title":"Grokking as Structural Inference: Transformers Need Bayesian Lottery Tickets","created":"2026-05-15","cited_by_count":1,"area":null},{"id":"2608.09558","title":"Training-Free Universal Approximation by Prompting Random Transformers","created":"2026-08-10","cited_by_count":1,"area":null},{"id":"2408.00359","title":"Memorization Capacity for Additive Fine-Tuning with Small ReLU Networks","created":"2024-08-01","cited_by_count":0,"area":null},{"id":"2510.11789","title":"Minimax Rates for Learning Pairwise Interactions in Attention-Style Models","created":"2025-10-13","cited_by_count":0,"area":null}],"next_cursor":null}