{"total":78,"rows":[{"id":"2212.10554","title":"A Length-Extrapolatable Transformer","created":"2022-12-20","cited_by_count":127,"area":null},{"id":"2402.09371","title":"Transformers Can Achieve Length Generalization But Not Robustly","created":"2024-02-14","cited_by_count":86,"area":null},{"id":"2405.17399","title":"Transformers Can Do Arithmetic with the Right Embeddings","created":"2024-05-27","cited_by_count":78,"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":"2410.23771","title":"What is Wrong with Perplexity for Long-context Language Modeling?","created":"2024-10-31","cited_by_count":69,"area":null},{"id":"2312.06528","title":"Transformers Implement Functional Gradient Descent to Learn Non-Linear Functions In Context","created":"2023-12-11","cited_by_count":63,"area":null},{"id":"2407.09450","title":"Human-inspired Episodic Memory for Infinite Context LLMs","created":"2024-07-12","cited_by_count":62,"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":"2503.02130","title":"Forgetting Transformer: Softmax Attention with a Forget Gate","created":"2025-03-03","cited_by_count":53,"area":null},{"id":"2501.18795","title":"Rope to Nope and Back Again: A New Hybrid Attention Strategy","created":"2025-01-30","cited_by_count":47,"area":null},{"id":"2310.16450","title":"CLEX: Continuous Length Extrapolation for Large Language Models","created":"2023-10-25","cited_by_count":44,"area":null},{"id":"2212.10356","title":"Dissecting Transformer Length Extrapolation via the Lens of Receptive Field Analysis","created":"2022-12-20","cited_by_count":42,"area":null},{"id":"2412.17739","title":"Fourier Position Embedding: Enhancing Attention's Periodic Extension for Length Generalization","created":"2024-12-23","cited_by_count":39,"area":null},{"id":"2405.14722","title":"DAPE: Data-Adaptive Positional Encoding for Length Extrapolation","created":"2024-05-23","cited_by_count":31,"area":null},{"id":"2305.19798","title":"Primal-Attention: Self-attention through Asymmetric Kernel SVD in Primal Representation","created":"2023-05-31","cited_by_count":29,"area":null},{"id":"2312.00678","title":"The Efficiency Spectrum of Large Language Models: An Algorithmic Survey","created":"2023-12-01","cited_by_count":26,"area":null},{"id":"2407.03310","title":"Universal Length Generalization with Turing Programs","created":"2024-07-03","cited_by_count":25,"area":null},{"id":"2401.16421","title":"Two Stones Hit One Bird: Bilevel Positional Encoding for Better Length Extrapolation","created":"2024-01-29","cited_by_count":24,"area":null},{"id":"2409.00509","title":"LongRecipe: Recipe for Efficient Long Context Generalization in Large Language Models","created":"2024-08-31","cited_by_count":23,"area":null},{"id":"2506.16640","title":"Long-Context Generalization with Sparse Attention","created":"2025-06-19","cited_by_count":21,"area":null},{"id":"2502.02562","title":"Learning the RoPEs: Better 2D and 3D Position Encodings with STRING","created":"2025-02-04","cited_by_count":19,"area":null},{"id":"2405.18009","title":"Exploring Context Window of Large Language Models via Decomposed Positional Vectors","created":"2024-05-28","cited_by_count":18,"area":null},{"id":"2307.09270","title":"Linearized Relative Positional Encoding","created":"2023-07-18","cited_by_count":17,"area":null},{"id":"2410.21216","title":"HoPE: A Novel Positional Encoding Without Long-Term Decay for Enhanced Context Awareness and Extrapolation","created":"2024-10-28","cited_by_count":17,"area":null},{"id":"2401.02317","title":"BA-SAM: Scalable Bias-Mode Attention Mask for Segment Anything Model","created":"2024-01-04","cited_by_count":15,"area":null},{"id":"2403.03514","title":"CLongEval: A Chinese Benchmark for Evaluating Long-Context Large Language Models","created":"2024-03-06","cited_by_count":15,"area":null},{"id":"2506.03131","title":"Native-Resolution Image Synthesis","created":"2025-06-03","cited_by_count":15,"area":null},{"id":"2305.03796","title":"Transformer Working Memory Enables Regular Language Reasoning and Natural Language Length Extrapolation","created":"2023-05-05","cited_by_count":13,"area":null},{"id":"2410.14195","title":"Rethinking Transformer for Long Contextual Histopathology Whole Slide Image Analysis","created":"2024-10-18","cited_by_count":12,"area":null},{"id":"2503.13299","title":"A Survey on Transformer Context Extension: Approaches and Evaluation","created":"2025-03-17","cited_by_count":11,"area":null},{"id":"2310.11984","title":"From Interpolation to Extrapolation: Complete Length Generalization for Arithmetic Transformers","created":"2023-10-18","cited_by_count":10,"area":null},{"id":"2410.04798","title":"DAPE V2: Process Attention Score as Feature Map for Length Extrapolation","created":"2024-10-07","cited_by_count":10,"area":null},{"id":"2509.05218","title":"HoPE: Hyperbolic Rotary Positional Encoding for Stable Long-Range Dependency Modeling in Large Language Models","created":"2025-09-05","cited_by_count":10,"area":null},{"id":"2311.00684","title":"Attention Alignment and Flexible Positional Embeddings Improve Transformer Length Extrapolation","created":"2023-11-01","cited_by_count":9,"area":null},{"id":"2511.17388","title":"Selective Rotary Position Embedding","created":"2025-11-21","cited_by_count":9,"area":null},{"id":"2307.10156","title":"Exploring Transformer Extrapolation","created":"2023-07-19","cited_by_count":8,"area":null},{"id":"2410.11474","title":"How Transformers Get Rich: Approximation and Dynamics Analysis","created":"2024-10-15","cited_by_count":8,"area":null},{"id":"2309.08646","title":"CoCA: Fusing Position Embedding with Collinear Constrained Attention in Transformers for Long Context Window Extending","created":"2023-09-15","cited_by_count":6,"area":null},{"id":"2504.02827","title":"On Vanishing Variance in Transformer Length Generalization","created":"2025-04-03","cited_by_count":6,"area":null},{"id":"2402.01476","title":"Self-Attention through Kernel-Eigen Pair Sparse Variational Gaussian Processes","created":"2024-02-02","cited_by_count":5,"area":null},{"id":"2505.13027","title":"Deconstructing Positional Information: From Attention Logits to Training Biases","created":"2025-05-19","cited_by_count":5,"area":null},{"id":"2511.09146","title":"DoPE: Denoising Rotary Position Embedding","created":"2025-11-12","cited_by_count":5,"area":null},{"id":"2512.07805","title":"Group Representational Position Encoding","created":"2025-12-08","cited_by_count":5,"area":null},{"id":"2503.19120","title":"Where is this coming from? Making groundedness count in the evaluation of Document VQA models","created":"2025-03-24","cited_by_count":4,"area":null},{"id":"2506.11769","title":"Long-Short Alignment for Effective Long-Context Modeling in LLMs","created":"2025-06-13","cited_by_count":4,"area":null},{"id":"2507.07694","title":"SAS: Simulated Attention Score","created":"2025-07-10","cited_by_count":4,"area":null},{"id":"2512.14391","title":"RePo: Language Models with Context Re-Positioning","created":"2025-12-16","cited_by_count":4,"area":null},{"id":"2311.12885","title":"Long-MIL: Scaling Long Contextual Multiple Instance Learning for Histopathology Whole Slide Image Analysis","created":"2023-11-21","cited_by_count":3,"area":null},{"id":"2403.17698","title":"MEP: Multiple Kernel Learning Enhancing Relative Positional Encoding Length Extrapolation","created":"2024-03-26","cited_by_count":3,"area":null},{"id":"2411.01035","title":"Provable Length Generalization in Sequence Prediction via Spectral Filtering","created":"2024-11-01","cited_by_count":3,"area":null},{"id":"2502.18277","title":"Self-Adjust Softmax","created":"2025-02-25","cited_by_count":3,"area":null},{"id":"2511.08368","title":"A Circular Argument : Does RoPE need to be Equivariant for Vision?","created":"2025-11-11","cited_by_count":3,"area":null},{"id":"2503.08067","title":"Context-aware Biases for Length Extrapolation","created":"2025-03-11","cited_by_count":2,"area":null},{"id":"2504.08129","title":"Between Linear and Sinusoidal: Rethinking the Time Encoder in Dynamic Graph Learning","created":"2025-04-10","cited_by_count":2,"area":null},{"id":"2606.11275","title":"RoVE: Rotary Value Embeddings Attention for Relative Position-dependent Value Pathways","created":"2026-06-09","cited_by_count":2,"area":null},{"id":"2311.11601","title":"Addressing the Length Bias Problem in Document-Level Neural Machine Translation","created":"2023-11-20","cited_by_count":1,"area":null},{"id":"2407.02109","title":"HRSAM: Efficient Interactive Segmentation in High-Resolution Images","created":"2024-07-02","cited_by_count":1,"area":null},{"id":"2501.13428","title":"Softplus Attention with Re-weighting Boosts Length Extrapolation in Large Language Models","created":"2025-01-23","cited_by_count":1,"area":null},{"id":"2603.04805","title":"Attention's Gravitational Field:A Power-Law Interpretation of Positional Correlation","created":"2026-02-06","cited_by_count":1,"area":null},{"id":"2605.04217","title":"Jordan-RoPE: Non-Semisimple Relative Positional Encoding via Complex Jordan Blocks","created":"2026-05-05","cited_by_count":1,"area":null},{"id":"2605.09472","title":"Positional LSH: Binary Block Matrix Approximation for Attention with Linear Biases","created":"2026-05-10","cited_by_count":1,"area":null},{"id":"2605.10414","title":"Remember to Forget: Gated Adaptive Positional Encoding","created":"2026-05-11","cited_by_count":1,"area":null},{"id":"2310.14633","title":"Extending Input Contexts of Language Models through Training on Segmented Sequences","created":"2023-10-23","cited_by_count":0,"area":null},{"id":"2505.00818","title":"Dual Filter: A Transformer-like Inference Architecture for Hidden Markov Models","created":"2025-05-01","cited_by_count":0,"area":null},{"id":"2506.08371","title":"Mitigating Posterior Salience Attenuation in Long-Context LLMs with Positional Contrastive Decoding","created":"2025-06-10","cited_by_count":0,"area":null},{"id":"2507.12780","title":"Compact Vision Transformer by Reduction of Kernel Complexity","created":"2025-07-17","cited_by_count":0,"area":null},{"id":"2509.26015","title":"Indirect Attention: Turning Context Misalignment into a Feature","created":"2025-09-30","cited_by_count":0,"area":null},{"id":"2512.05385","title":"ShaRP: SHAllow-LayeR Pruning for Efficient Video Large Language Models","created":"2025-12-05","cited_by_count":0,"area":null},{"id":"2512.19323","title":"Alternative positional encoding functions for neural transformers","created":"2025-12-22","cited_by_count":0,"area":null},{"id":"2602.00596","title":"Kernelized Edge Attention: Addressing Semantic Attention Blurring in Temporal Graph Neural Networks","created":"2026-01-31","cited_by_count":0,"area":null},{"id":"2602.14050","title":"Position Encoding with Random Float Sampling Enhances Length Generalization of Transformers","created":"2026-02-15","cited_by_count":0,"area":null},{"id":"2605.26067","title":"Conditional KRR: Injecting Unpenalized Features into Kernel Methods with Applications to Kernel Thresholding","created":"2026-05-25","cited_by_count":0,"area":null},{"id":"2605.30022","title":"Give it Space! Explicit Disentangling of Positional and Semantic Representations in Encoders","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2606.05345","title":"PJ-RoPE: A Fourier-Jet-Affine Position Space for Relative Attention","created":"2026-06-03","cited_by_count":0,"area":null},{"id":"2608.03994","title":"When Attention Goes Blind: Numerical Failure in ALiBi Positional Encodings","created":"2026-08-04","cited_by_count":0,"area":null},{"id":"2608.20172","title":"Ask Self, Ask Others: Relation Is All You Need","created":"2026-08-20","cited_by_count":0,"area":null},{"id":"2609.34556","title":"RoPE is Dead, Long Live RoPE: Towards Scalable Data-aware Positional Encodings","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2610.04518","title":"Length Generalization Needs Proper Regularization","created":"2026-10-03","cited_by_count":0,"area":null}],"next_cursor":null}