{"total":72,"rows":[{"id":"2302.11939","title":"One Fits All:Power General Time Series Analysis by Pretrained LM","created":"2023-02-23","cited_by_count":632,"area":null},{"id":"2106.03893","title":"Rethinking Graph Transformers with Spectral Attention","created":"2021-06-07","cited_by_count":473,"area":null},{"id":"2306.09927","title":"Trained Transformers Learn Linear Models In-Context","created":"2023-06-16","cited_by_count":337,"area":null},{"id":"2303.06147","title":"Exphormer: Sparse Transformers for Graphs","created":"2023-03-10","cited_by_count":170,"area":null},{"id":"2202.08625","title":"Revisiting Over-smoothing in BERT from the Perspective of Graph","created":"2022-02-17","cited_by_count":72,"area":null},{"id":"2311.12351","title":"Advancing Transformer Architecture in Long-Context Large Language Models: A Comprehensive Survey","created":"2023-11-21","cited_by_count":72,"area":null},{"id":"2305.15805","title":"Dynamic Context Pruning for Efficient and Interpretable Autoregressive Transformers","created":"2023-05-25","cited_by_count":67,"area":null},{"id":"2107.05768","title":"Combiner: Full Attention Transformer with Sparse Computation Cost","created":"2021-07-12","cited_by_count":64,"area":null},{"id":"2502.01951","title":"On the Emergence of Position Bias in Transformers","created":"2025-02-04","cited_by_count":59,"area":null},{"id":"2205.13401","title":"Your Transformer May Not be as Powerful as You Expect","created":"2022-05-26","cited_by_count":55,"area":null},{"id":"2109.04312","title":"MATE: Multi-view Attention for Table Transformer Efficiency","created":"2021-09-09","cited_by_count":54,"area":null},{"id":"2303.08117","title":"Do Transformers Parse while Predicting the Masked Word?","created":"2023-03-14","cited_by_count":48,"area":null},{"id":"2405.18781","title":"On the Role of Attention Masks and LayerNorm in Transformers","created":"2024-05-29","cited_by_count":48,"area":null},{"id":"2106.03764","title":"On the Expressive Power of Self-Attention Matrices","created":"2021-06-07","cited_by_count":47,"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":"2102.12871","title":"SparseBERT: Rethinking the Importance Analysis in Self-attention","created":"2021-02-25","cited_by_count":46,"area":null},{"id":"2412.12094","title":"SepLLM: Accelerate Large Language Models by Compressing One Segment into One Separator","created":"2024-12-16","cited_by_count":41,"area":null},{"id":"2306.02010","title":"Memorization Capacity of Multi-Head Attention in Transformers","created":"2023-06-03","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":"2403.08081","title":"Mechanics of Next Token Prediction with Self-Attention","created":"2024-03-12","cited_by_count":34,"area":null},{"id":"2110.06821","title":"Leveraging redundancy in attention with Reuse Transformers","created":"2021-10-13","cited_by_count":33,"area":null},{"id":"2110.03303","title":"Universal Approximation Under Constraints is Possible with Transformers","created":"2021-10-07","cited_by_count":32,"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":"2205.08078","title":"Unraveling Attention via Convex Duality: Analysis and Interpretations of Vision Transformers","created":"2022-05-17","cited_by_count":30,"area":null},{"id":"2307.02301","title":"Sumformer: Universal Approximation for Efficient Transformers","created":"2023-07-05","cited_by_count":30,"area":null},{"id":"2305.18475","title":"Approximation Rate of the Transformer Architecture for Sequence Modeling","created":"2023-05-29","cited_by_count":28,"area":null},{"id":"2111.01353","title":"Can Vision Transformers Perform Convolution?","created":"2021-11-02","cited_by_count":18,"area":null},{"id":"2403.06082","title":"FrameQuant: Flexible Low-Bit Quantization for Transformers","created":"2024-03-10","cited_by_count":18,"area":null},{"id":"2201.09332","title":"How Expressive are Transformers in Spectral Domain for Graphs?","created":"2022-01-23","cited_by_count":15,"area":null},{"id":"2203.06462","title":"Low-Rank Softmax Can Have Unargmaxable Classes in Theory but Rarely in Practice","created":"2022-03-12","cited_by_count":15,"area":null},{"id":"2302.13752","title":"A Brief Survey on the Approximation Theory for Sequence Modelling","created":"2023-02-27","cited_by_count":15,"area":null},{"id":"2210.11794","title":"Diffuser: Efficient Transformers with Multi-hop Attention Diffusion for Long Sequences","created":"2022-10-21","cited_by_count":12,"area":null},{"id":"2502.09844","title":"Solving Empirical Bayes via Transformers","created":"2025-02-14","cited_by_count":11,"area":null},{"id":"2302.01925","title":"Learning a Fourier Transform for Linear Relative Positional Encodings in Transformers","created":"2023-02-03","cited_by_count":10,"area":null},{"id":"2409.17677","title":"On the Optimal Memorization Capacity of Transformers","created":"2024-09-26","cited_by_count":10,"area":null},{"id":"2208.09015","title":"Treeformer: Dense Gradient Trees for Efficient Attention Computation","created":"2022-08-18","cited_by_count":9,"area":null},{"id":"2309.06589","title":"Do Generative Large Language Models need billions of parameters?","created":"2023-09-12","cited_by_count":8,"area":null},{"id":"2106.08823","title":"Eigen Analysis of Self-Attention and its Reconstruction from Partial Computation","created":"2021-06-16","cited_by_count":6,"area":null},{"id":"2402.15478","title":"Transformers are Expressive, But Are They Expressive Enough for Regression?","created":"2024-02-23","cited_by_count":6,"area":null},{"id":"2408.08258","title":"Snuffy: Efficient Whole Slide Image Classifier","created":"2024-08-15","cited_by_count":6,"area":null},{"id":"2407.14106","title":"TorchGT: A Holistic System for Large-scale Graph Transformer Training","created":"2024-07-19","cited_by_count":5,"area":null},{"id":"2504.13558","title":"Transformers Can Overcome the Curse of Dimensionality: A Theoretical Study from an Approximation Perspective","created":"2025-04-18","cited_by_count":5,"area":null},{"id":"2202.12166","title":"Attention Enables Zero Approximation Error","created":"2022-02-24","cited_by_count":4,"area":null},{"id":"2210.15541","title":"Transformers meet Stochastic Block Models: Attention with Data-Adaptive Sparsity and Cost","created":"2022-10-27","cited_by_count":4,"area":null},{"id":"2409.00297","title":"On Expressive Power of Quantized Neural Networks under Fixed-Point Arithmetic","created":"2024-08-30","cited_by_count":4,"area":null},{"id":"2504.12175","title":"Approximation Bounds for Transformer Networks with Application to Regression","created":"2025-04-16","cited_by_count":4,"area":null},{"id":"2510.06662","title":"The Effect of Attention Head Count on Transformer Approximation","created":"2025-10-08","cited_by_count":4,"area":null},{"id":"2402.05955","title":"A Hyper-Transformer model for Controllable Pareto Front Learning with Split Feasibility Constraints","created":"2024-02-04","cited_by_count":3,"area":null},{"id":"2406.19391","title":"Fibottention: Inceptive Visual Representation Learning with Diverse Attention Across Heads","created":"2024-06-27","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":"2507.03117","title":"BLaST: High Performance Inference and Pretraining using BLock Sparse Transformers","created":"2025-07-03","cited_by_count":3,"area":null},{"id":"2503.10632","title":"Kolmogorov-Arnold Attention: Is Learnable Attention Better For Vision Transformers?","created":"2025-03-13","cited_by_count":2,"area":null},{"id":"2506.12220","title":"Two Heads Are Better than One: Simulating Large Transformers with Small Ones","created":"2025-06-13","cited_by_count":2,"area":null},{"id":"2506.23551","title":"A unified framework for establishing the universal approximation of transformer-type architectures","created":"2025-06-30","cited_by_count":2,"area":null},{"id":"2601.16450","title":"On the Expressive Power of Floating-Point Transformers","created":"2026-01-23","cited_by_count":2,"area":null},{"id":"2605.08811","title":"Learning Theory of Transformers: Local-to-Global Approximation via Softmax Partition of Unity","created":"2026-05-09","cited_by_count":2,"area":null},{"id":"2607.07678","title":"How Data Shapes RoPE Frequency Usage: From Positional Scale Matching to Length Generalization","created":"2026-07-08","cited_by_count":2,"area":null},{"id":"2201.03327","title":"Latency Adjustable Transformer Encoder for Language Understanding","created":"2022-01-10","cited_by_count":1,"area":null},{"id":"2302.14346","title":"Sampled Transformer for Point Sets","created":"2023-02-28","cited_by_count":1,"area":null},{"id":"2406.12915","title":"How Out-of-Distribution Detection Learning Theory Enhances Transformer: Learnability and Reliability","created":"2024-06-13","cited_by_count":1,"area":null},{"id":"2603.03084","title":"On the Expressive Power of Transformers for Maxout Networks and Continuous Piecewise Linear Functions","created":"2026-03-03","cited_by_count":1,"area":null},{"id":"2606.17522","title":"An expressivity analysis of hierarchical modelling in deep transformers via bounded-depth grammars","created":"2026-06-16","cited_by_count":1,"area":null},{"id":"2609.35483","title":"Universal Approximation of Measure-to-Measure Operators by Pushforwards","created":"2026-09-28","cited_by_count":1,"area":null},{"id":"2106.00047","title":"Learning and Generalization in RNNs","created":"2021-05-31","cited_by_count":0,"area":null},{"id":"2407.00958","title":"Dynamic Universal Approximation Theory: The Basic Theory for Transformer-based Large Language Models","created":"2024-07-01","cited_by_count":0,"area":null},{"id":"2508.01134","title":"Transformers in Pseudo-Random Number Generation: A Dual Perspective on Theory and Practice","created":"2025-08-02","cited_by_count":0,"area":null},{"id":"2512.18445","title":"On the Universality of Transformer Architectures; How Much Attention Is Enough?","created":"2025-12-20","cited_by_count":0,"area":null},{"id":"2604.03815","title":"k-Maximum Inner Product Attention for Graph Transformers and the Expressive Power of GraphGPS","created":"2026-04-04","cited_by_count":0,"area":null},{"id":"2605.17930","title":"InfoFlow: A Framework for Multi-Layer Transformer Analysis","created":"2026-05-18","cited_by_count":0,"area":null},{"id":"2605.22223","title":"How Many Different Outputs Can a Transformer Generate?","created":"2026-05-21","cited_by_count":0,"area":null},{"id":"2606.27372","title":"DnA: Denoising Attention for Visual Tasks","created":"2026-06-25","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}],"next_cursor":null}