{"total":42,"rows":[{"id":"2407.02490","title":"MInference 1.0: Accelerating Pre-filling for Long-Context LLMs via Dynamic Sparse Attention","created":"2024-07-02","cited_by_count":383,"area":null},{"id":"2306.09927","title":"Trained Transformers Learn Linear Models In-Context","created":"2023-06-16","cited_by_count":337,"area":null},{"id":"2207.02505","title":"Pure Transformers are Powerful Graph Learners","created":"2022-07-06","cited_by_count":188,"area":null},{"id":"2110.10090","title":"Inductive Biases and Variable Creation in Self-Attention Mechanisms","created":"2021-10-19","cited_by_count":144,"area":null},{"id":"2306.02896","title":"Representational Strengths and Limitations of Transformers","created":"2023-06-05","cited_by_count":133,"area":null},{"id":"2502.20766","title":"FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference","created":"2025-02-28","cited_by_count":123,"area":null},{"id":"2305.16380","title":"Scan and Snap: Understanding Training Dynamics and Token Composition in 1-layer Transformer","created":"2023-05-25","cited_by_count":102,"area":null},{"id":"2402.09268","title":"Transformers, parallel computation, and logarithmic depth","created":"2024-02-14","cited_by_count":79,"area":null},{"id":"2302.06015","title":"A Theoretical Understanding of Shallow Vision Transformers: Learning, Generalization, and Sample Complexity","created":"2023-02-12","cited_by_count":77,"area":null},{"id":"2403.04797","title":"Found in the Middle: How Language Models Use Long Contexts Better via Plug-and-Play Positional Encoding","created":"2024-03-05","cited_by_count":72,"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":"2307.14023","title":"Are Transformers with One Layer Self-Attention Using Low-Rank Weight Matrices Universal Approximators?","created":"2023-07-26","cited_by_count":47,"area":null},{"id":"2312.14820","title":"How Smooth Is Attention?","created":"2023-12-22","cited_by_count":44,"area":null},{"id":"2310.19698","title":"When Do Prompting and Prefix-Tuning Work? A Theory of Capabilities and Limitations","created":"2023-10-30","cited_by_count":43,"area":null},{"id":"2406.15486","title":"SampleAttention: Near-Lossless Acceleration of Long Context LLM Inference with Adaptive Structured Sparse Attention","created":"2024-06-17","cited_by_count":39,"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":"2305.18699","title":"Approximation and Estimation Ability of Transformers for Sequence-to-Sequence Functions with Infinite Dimensional Input","created":"2023-05-30","cited_by_count":32,"area":null},{"id":"2307.02301","title":"Sumformer: Universal Approximation for Efficient Transformers","created":"2023-07-05","cited_by_count":30,"area":null},{"id":"2402.14753","title":"Prompting a Pretrained Transformer Can Be a Universal Approximator","created":"2024-02-22","cited_by_count":25,"area":null},{"id":"2402.11639","title":"In-Context Learning with Transformers: Softmax Attention Adapts to Function Lipschitzness","created":"2024-02-18","cited_by_count":22,"area":null},{"id":"2406.06893","title":"Transformers Provably Learn Sparse Token Selection While Fully-Connected Nets Cannot","created":"2024-06-11","cited_by_count":22,"area":null},{"id":"2111.01353","title":"Can Vision Transformers Perform Convolution?","created":"2021-11-02","cited_by_count":18,"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":"2509.24745","title":"ProxyAttn: Guided Sparse Attention via Representative Heads","created":"2025-09-29","cited_by_count":9,"area":null},{"id":"2112.10644","title":"Self-attention Presents Low-dimensional Knowledge Graph Embeddings for Link Prediction","created":"2021-12-20","cited_by_count":8,"area":null},{"id":"2506.05200","title":"Transformers Meet In-Context Learning: A Universal Approximation Theory","created":"2025-06-05","cited_by_count":6,"area":null},{"id":"2308.05219","title":"Decoding Layer Saliency in Language Transformers","created":"2023-08-09","cited_by_count":5,"area":null},{"id":"2411.13028","title":"A Theory for Compressibility of Graph Transformers for Transductive Learning","created":"2024-11-20","cited_by_count":3,"area":null},{"id":"2502.11467","title":"Approximation of Permutation Invariant Polynomials by Transformers: Efficient Construction in Column-Size","created":"2025-02-17","cited_by_count":3,"area":null},{"id":"2503.11272","title":"When Do Transformers Outperform Feedforward and Recurrent Networks? A Statistical Perspective","created":"2025-03-14","cited_by_count":3,"area":null},{"id":"2606.00605","title":"Looped Transformers with Layer Normalization Provably Learn the Power Method","created":"2026-05-30","cited_by_count":2,"area":null},{"id":"2305.18385","title":"Self-attention Dual Embedding for Graphs with Heterophily","created":"2023-05-28","cited_by_count":1,"area":null},{"id":"2601.05647","title":"Transformer Is Inherently a Causal Learner","created":"2026-01-09","cited_by_count":1,"area":null},{"id":"2503.01564","title":"Attention Condensation via Sparsity Induced Regularized Training","created":"2025-03-03","cited_by_count":0,"area":null},{"id":"2509.22307","title":"Johnson-Lindenstrauss Lemma Guided Network for Efficient 3D Medical Segmentation","created":"2025-09-26","cited_by_count":0,"area":null},{"id":"2511.06376","title":"Vocabulary In-Context Learning in Transformers: Benefits of Positional Encoding","created":"2025-11-09","cited_by_count":0,"area":null},{"id":"2604.19147","title":"Nexusformer: Nonlinear Attention Expansion for Stable and Inheritable Transformer Scaling","created":"2026-04-21","cited_by_count":0,"area":null},{"id":"2605.25619","title":"Analogies between Transformer Layers and Power Method","created":"2026-05-25","cited_by_count":0,"area":null},{"id":"2609.01925","title":"CRISP: Cliff-awaRe Input-adaptive Sparse Prefilling with Structural-Mass-Motivated Routing","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.34731","title":"Information-Theoretic Analysis of Next-Token Prediction under Markovian Data","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2610.04424","title":"On the Trade-off Between Information Loss and Generalization in Sparse Attention","created":"2026-10-03","cited_by_count":0,"area":null},{"id":"2610.13518","title":"Asymptotic Analysis of Discrete-Time Self-Attention Dynamics in Transformers","created":"2026-10-09","cited_by_count":0,"area":null}],"next_cursor":null}