{"total":94,"rows":[{"id":"2308.14508","title":"LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding","created":"2023-08-28","cited_by_count":1417,"area":null},{"id":"2404.06654","title":"RULER: What's the Real Context Size of Your Long-Context Language Models?","created":"2024-04-09","cited_by_count":1346,"area":null},{"id":"2403.07815","title":"Chronos: Learning the Language of Time Series","created":"2024-03-12","cited_by_count":759,"area":null},{"id":"2307.08621","title":"Retentive Network: A Successor to Transformer for Large Language Models","created":"2023-07-17","cited_by_count":613,"area":null},{"id":"2305.16300","title":"Landmark Attention: Random-Access Infinite Context Length for Transformers","created":"2023-05-25","cited_by_count":213,"area":null},{"id":"2307.02486","title":"LongNet: Scaling Transformers to 1,000,000,000 Tokens","created":"2023-07-05","cited_by_count":204,"area":null},{"id":"2312.03863","title":"Efficient Large Language Models: A Survey","created":"2023-12-06","cited_by_count":186,"area":null},{"id":"2402.10171","title":"Data Engineering for Scaling Language Models to 128K Context","created":"2024-02-15","cited_by_count":186,"area":null},{"id":"2401.01325","title":"LLM Maybe LongLM: Self-Extend LLM Context Window Without Tuning","created":"2024-01-02","cited_by_count":136,"area":null},{"id":"2310.05209","title":"Scaling Laws of RoPE-based Extrapolation","created":"2023-10-08","cited_by_count":125,"area":null},{"id":"2309.10400","title":"PoSE: Efficient Context Window Extension of LLMs via Positional Skip-wise Training","created":"2023-09-19","cited_by_count":111,"area":null},{"id":"2307.13721","title":"Foundational Models Defining a New Era in Vision: A Survey and Outlook","created":"2023-07-25","cited_by_count":110,"area":null},{"id":"2402.04624","title":"MEMORYLLM: Towards Self-Updatable Large Language Models","created":"2024-02-07","cited_by_count":93,"area":null},{"id":"2412.09548","title":"Meshtron: High-Fidelity, Artist-Like 3D Mesh Generation at Scale","created":"2024-12-12","cited_by_count":89,"area":null},{"id":"2401.08092","title":"A Survey of Resource-efficient LLM and Multimodal Foundation Models","created":"2024-01-16","cited_by_count":86,"area":null},{"id":"2310.10375","title":"GTA: A Geometry-Aware Attention Mechanism for Multi-View Transformers","created":"2023-10-16","cited_by_count":79,"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":"2505.14766","title":"This Time is Different: An Observability Perspective on Time Series Foundation Models","created":"2025-05-20","cited_by_count":68,"area":null},{"id":"2309.07062","title":"Large Language Models for Compiler Optimization","created":"2023-09-11","cited_by_count":52,"area":null},{"id":"2405.14591","title":"Base of RoPE Bounds Context Length","created":"2024-05-23","cited_by_count":52,"area":null},{"id":"2407.07874","title":"Toto: Time Series Optimized Transformer for Observability","created":"2024-07-10","cited_by_count":48,"area":null},{"id":"2502.01563","title":"Massive Values in Self-Attention Modules are the Key to Contextual Knowledge Understanding","created":"2025-02-03","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":"2405.14722","title":"DAPE: Data-Adaptive Positional Encoding for Length Extrapolation","created":"2024-05-23","cited_by_count":31,"area":null},{"id":"2402.00059","title":"FengWu-GHR: Learning the Kilometer-scale Medium-range Global Weather Forecasting","created":"2024-01-28","cited_by_count":30,"area":null},{"id":"2310.03294","title":"DISTFLASHATTN: Distributed Memory-efficient Attention for Long-context LLMs Training","created":"2023-10-05","cited_by_count":29,"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":"2309.03852","title":"FLM-101B: An Open LLM and How to Train It with $100K Budget","created":"2023-09-07","cited_by_count":22,"area":null},{"id":"2309.11568","title":"BTLM-3B-8K: 7B Parameter Performance in a 3B Parameter Model","created":"2023-09-20","cited_by_count":19,"area":null},{"id":"2311.10609","title":"Scaling TabPFN: Sketching and Feature Selection for Tabular Prior-Data Fitted Networks","created":"2023-11-17","cited_by_count":18,"area":null},{"id":"2405.06107","title":"Transforming the Bootstrap: Using Transformers to Compute Scattering Amplitudes in Planar N = 4 Super Yang-Mills Theory","created":"2024-05-09","cited_by_count":18,"area":null},{"id":"2406.19598","title":"Mixture of In-Context Experts Enhance LLMs' Long Context Awareness","created":"2024-06-28","cited_by_count":17,"area":null},{"id":"2310.19240","title":"M4LE: A Multi-Ability Multi-Range Multi-Task Multi-Domain Long-Context Evaluation Benchmark for Large Language Models","created":"2023-10-30","cited_by_count":15,"area":null},{"id":"2409.13265","title":"Towards LifeSpan Cognitive Systems","created":"2024-09-20","cited_by_count":13,"area":null},{"id":"2404.16645","title":"Tele-FLM Technical Report","created":"2024-04-25","cited_by_count":12,"area":null},{"id":"2310.00576","title":"GrowLength: Accelerating LLMs Pretraining by Progressively Growing Training Length","created":"2023-10-01","cited_by_count":11,"area":null},{"id":"2404.00560","title":"A Theory for Length Generalization in Learning to Reason","created":"2024-03-31","cited_by_count":11,"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":"2509.10534","title":"Decoupling the \"What\" and \"Where\" With Polar Coordinate Positional Embeddings","created":"2025-09-05","cited_by_count":10,"area":null},{"id":"2305.20019","title":"Monotonic Location Attention for Length Generalization","created":"2023-05-31","cited_by_count":9,"area":null},{"id":"2506.11440","title":"AbsenceBench: Language Models Can't Tell What's Missing","created":"2025-06-13","cited_by_count":9,"area":null},{"id":"2506.07405","title":"RiemannFormer: A Framework for Attention in Curved Spaces","created":"2025-06-09","cited_by_count":8,"area":null},{"id":"2310.08796","title":"End-to-end Story Plot Generator","created":"2023-10-13","cited_by_count":7,"area":null},{"id":"2410.06577","title":"Rodimus*: Breaking the Accuracy-Efficiency Trade-Off with Efficient Attentions","created":"2024-10-09","cited_by_count":6,"area":null},{"id":"2402.00976","title":"Investigating Recurrent Transformers with Dynamic Halt","created":"2024-02-01","cited_by_count":5,"area":null},{"id":"2506.11111","title":"Evaluating and Improving Robustness in Large Language Models: A Survey and Future Directions","created":"2025-06-08","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":"2305.04859","title":"A Frustratingly Easy Improvement for Position Embeddings via Random Padding","created":"2023-05-08","cited_by_count":4,"area":null},{"id":"2312.00817","title":"TimelyGPT: Extrapolatable Transformer Pre-training for Long-term Time-Series Forecasting in Healthcare","created":"2023-11-29","cited_by_count":4,"area":null},{"id":"2312.06594","title":"Mitigating Perspective Distortion-induced Shape Ambiguity in Image Crops","created":"2023-12-11","cited_by_count":4,"area":null},{"id":"2312.09004","title":"Holistic chemical evaluation reveals pitfalls in reaction prediction models","created":"2023-12-14","cited_by_count":4,"area":null},{"id":"2411.03900","title":"Retentive Neural Quantum States: Efficient Ans\\\"atze for Ab Initio Quantum Chemistry","created":"2024-11-06","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":"2601.22181","title":"MrRoPE: Mixed-radix Rotary Position Embedding","created":"2026-01-28","cited_by_count":4,"area":null},{"id":"2406.04342","title":"Learning 1D Causal Visual Representation with De-focus Attention Networks","created":"2024-06-06","cited_by_count":3,"area":null},{"id":"2601.00919","title":"Attention Needs to Focus: A Unified Perspective on Attention Allocation","created":"2026-01-01","cited_by_count":3,"area":null},{"id":"2308.10252","title":"LMTuner: An user-friendly and highly-integrable Training Framework for fine-tuning Large Language Models","created":"2023-08-20","cited_by_count":2,"area":null},{"id":"2310.19731","title":"ViR: Towards Efficient Vision Retention Backbones","created":"2023-10-30","cited_by_count":2,"area":null},{"id":"2402.09558","title":"Bidirectional Generative Pre-training for Improving Healthcare Time-series Representation Learning","created":"2024-02-14","cited_by_count":2,"area":null},{"id":"2412.05517","title":"Test-time Cost-and-Quality Controllable Arbitrary-Scale Super-Resolution with Variable Fourier Components","created":"2024-12-07","cited_by_count":2,"area":null},{"id":"2503.07680","title":"Hierarchical Balance Packing: Towards Efficient Supervised Fine-tuning for Long-Context LLM","created":"2025-03-10","cited_by_count":2,"area":null},{"id":"2605.00968","title":"Adaptive 3D-RoPE: Physics-Aligned Rotary Positional Encoding for Wireless Foundation Models","created":"2026-05-01","cited_by_count":2,"area":null},{"id":"2609.24559","title":"$t_0$: A Time-Series Foundation Model for Forecasting with Context","created":"2026-09-21","cited_by_count":2,"area":null},{"id":"2402.17512","title":"Unifying Linear-Time Attention via Latent Probabilistic Modelling","created":"2024-02-27","cited_by_count":1,"area":null},{"id":"2409.01531","title":"On the Design Space Between Transformers and Recursive Neural Nets","created":"2024-09-03","cited_by_count":1,"area":null},{"id":"2410.04056","title":"RetCompletion:High-Speed Inference Image Completion with Retentive Network","created":"2024-10-05","cited_by_count":1,"area":null},{"id":"2509.04154","title":"Robust Filter Attention: Self-Attention as Precision-Weighted State Estimation","created":"2025-09-04","cited_by_count":1,"area":null},{"id":"2509.12635","title":"Positional Encoding via Token-Aware Phase Attention","created":"2025-09-16","cited_by_count":1,"area":null},{"id":"2509.23109","title":"AttAnchor: Guiding Cross-Modal Token Alignment in VLMs with Attention Anchors","created":"2025-09-27","cited_by_count":1,"area":null},{"id":"2510.18830","title":"MTraining: Distributed Dynamic Sparse Attention for Efficient Ultra-Long Context Training","created":"2025-10-21","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":"2401.10286","title":"Code-Based English Models Surprising Performance on Chinese QA Pair Extraction Task","created":"2024-01-16","cited_by_count":0,"area":null},{"id":"2410.01637","title":"On The Adaptation of Unlimiformer for Decoder-Only Transformers","created":"2024-10-02","cited_by_count":0,"area":null},{"id":"2410.18160","title":"Future Token Prediction -- Causal Language Modelling with Per-Token Semantic State Vector for Multi-Token Prediction","created":"2024-10-23","cited_by_count":0,"area":null},{"id":"2501.12896","title":"Irrational Complex Rotations Empower Low-bit Optimizers","created":"2025-01-22","cited_by_count":0,"area":null},{"id":"2503.02534","title":"SAGE-Amine: Generative Amine Design with Multi-Property Optimization for Efficient CO2 Capture","created":"2025-03-04","cited_by_count":0,"area":null},{"id":"2507.10464","title":"AudioMAE++: learning better masked audio representations with SwiGLU FFNs","created":"2025-07-14","cited_by_count":0,"area":null},{"id":"2509.03973","title":"SAC-MIL: Spatial-Aware Correlated Multiple Instance Learning for Histopathology Whole Slide Image Classification","created":"2025-09-04","cited_by_count":0,"area":null},{"id":"2509.16629","title":"Causality-Induced Positional Encoding for Transformer-Based Representation Learning of Non-Sequential Features","created":"2025-09-20","cited_by_count":0,"area":null},{"id":"2510.09767","title":"HeSRN: Representation Learning On Heterogeneous Graphs via Slot-Aware Retentive Network","created":"2025-10-10","cited_by_count":0,"area":null},{"id":"2602.01418","title":"Parabolic Position Encoding: Vision-Centric, Principled, Extrapolatable, General","created":"2026-02-01","cited_by_count":0,"area":null},{"id":"2604.18603","title":"Dual Triangle Attention: Effective Bidirectional Attention Without Positional Embeddings","created":"2026-04-09","cited_by_count":0,"area":null},{"id":"2605.11007","title":"The Transformer as a Polar State Estimator","created":"2026-05-10","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":"2608.10296","title":"Cracks in the Foundation: Seemingly Minor Architectural Choices Impact Long Context Extension","created":"2026-08-10","cited_by_count":0,"area":null},{"id":"2609.09157","title":"Learning Length-Extrapolatable Recurrent Models","created":"2026-09-08","cited_by_count":0,"area":null},{"id":"2609.31261","title":"MoSAR: Mixture of Semantic Attention Regimes for Learning Adaptive and Approximable Attention Geometries","created":"2026-09-25","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},{"id":"2610.06963","title":"WavePrune: One period is often enough for RoPE","created":"2026-10-03","cited_by_count":0,"area":null},{"id":"2610.12657","title":"Kronecker Product Attention: Memory-Efficient KV Compression via Structured Factorization","created":"2026-10-08","cited_by_count":0,"area":null},{"id":"2610.19358","title":"Asymptotic Behavior of Transformers","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}