{"total":43,"rows":[{"id":"2507.10496","title":"Cameras as Relative Positional Encoding","created":"2025-07-14","cited_by_count":105,"area":null},{"id":"2410.04803","title":"Timer-XL: Long-Context Transformers for Unified Time Series Forecasting","created":"2024-10-07","cited_by_count":87,"area":null},{"id":"2404.08801","title":"Megalodon: Efficient LLM Pretraining and Inference with Unlimited Context Length","created":"2024-04-12","cited_by_count":46,"area":null},{"id":"2502.08942","title":"Language in the Flow of Time: Time-Series-Paired Texts Weaved into a Unified Temporal Narrative","created":"2025-02-13","cited_by_count":40,"area":null},{"id":"2503.14443","title":"EnvBench: A Benchmark for Automated Environment Setup","created":"2025-03-18","cited_by_count":36,"area":null},{"id":"2410.05076","title":"TidalDecode: Fast and Accurate LLM Decoding with Position Persistent Sparse Attention","created":"2024-10-07","cited_by_count":29,"area":null},{"id":"2412.18537","title":"Harnessing Large Language Models for Knowledge Graph Question Answering via Adaptive Multi-Aspect Retrieval-Augmentation","created":"2024-12-24","cited_by_count":24,"area":null},{"id":"2410.00487","title":"Self-Updatable Large Language Models by Integrating Context into Model Parameters","created":"2024-10-01","cited_by_count":21,"area":null},{"id":"2411.10478","title":"Large Language Models for Constructing and Optimizing Machine Learning Workflows: A Survey","created":"2024-11-11","cited_by_count":19,"area":null},{"id":"2409.03258","title":"GraphInsight: Unlocking Insights in Large Language Models for Graph Structure Understanding","created":"2024-09-05","cited_by_count":18,"area":null},{"id":"2409.13265","title":"Towards LifeSpan Cognitive Systems","created":"2024-09-20","cited_by_count":13,"area":null},{"id":"2406.09477","title":"Q-S5: Towards Quantized State Space Models","created":"2024-06-13","cited_by_count":10,"area":null},{"id":"2506.00069","title":"Evaluating the Sensitivity of LLMs to Prior Context","created":"2025-05-29","cited_by_count":9,"area":null},{"id":"2508.10824","title":"Memory-Augmented Transformers: A Systematic Review from Neuroscience Principles to Enhanced Model Architectures","created":"2025-08-14","cited_by_count":9,"area":null},{"id":"2506.13992","title":"AssistedDS: Benchmarking How External Domain Knowledge Assists LLMs in Automated Data Science","created":"2025-05-25","cited_by_count":7,"area":null},{"id":"2508.18224","title":"FSA: An Alternative Efficient Implementation of Native Sparse Attention Kernel","created":"2025-08-25","cited_by_count":7,"area":null},{"id":"2409.11192","title":"Towards Ethical Personal AI Applications: Practical Considerations for AI Assistants with Long-Term Memory","created":"2024-09-17","cited_by_count":6,"area":null},{"id":"2502.01812","title":"SelfCheck-Eval: A Multi-Module Framework for Zero-Resource Hallucination Detection in Large Language Models","created":"2025-02-03","cited_by_count":4,"area":null},{"id":"2505.23838","title":"Exploring the Landscape of Text-to-SQL with Large Language Models: Progresses, Challenges and Opportunities","created":"2025-05-28","cited_by_count":4,"area":null},{"id":"2508.00507","title":"Court of LLMs: Evidence-Augmented Generation via Multi-LLM Collaboration for Text-Attributed Graph Anomaly Detection","created":"2025-08-01","cited_by_count":3,"area":null},{"id":"2603.20105","title":"The $\\mathbf{Y}$-Combinator for LLMs: Solving Long-Context Rot with $\\lambda$-Calculus","created":"2026-03-20","cited_by_count":3,"area":null},{"id":"2412.02819","title":"CNNSum: Exploring Long-Context Summarization with Large Language Models in Chinese Novels","created":"2024-12-03","cited_by_count":2,"area":null},{"id":"2502.08363","title":"Top-Theta Attention: Sparsifying Transformers by Compensated Thresholding","created":"2025-02-12","cited_by_count":2,"area":null},{"id":"2505.14752","title":"LLMSynthor: Macro-Aligned Micro-Records Synthesis with Large Language Models","created":"2025-05-20","cited_by_count":1,"area":null},{"id":"2509.01185","title":"Modular Techniques for Synthetic Long-Context Data Generation in Language Model Training and Evaluation","created":"2025-09-01","cited_by_count":1,"area":null},{"id":"2512.20245","title":"Memory as Resonance: A Biomimetic Architecture for Infinite Context Memory on Ergodic Phonetic Manifolds","created":"2025-12-23","cited_by_count":1,"area":null},{"id":"2606.27791","title":"NLL-Guided Full-Attention Layer Selection for Training-Free Sliding-Window Adaptation","created":"2026-06-26","cited_by_count":1,"area":null},{"id":"2407.20197","title":"Learning Random Numbers to Realize Appendable Memory System for Artificial Intelligence to Acquire New Knowledge after Deployment","created":"2024-07-29","cited_by_count":0,"area":null},{"id":"2410.10553","title":"SLaNC: Static LayerNorm Calibration","created":"2024-10-14","cited_by_count":0,"area":null},{"id":"2501.13188","title":"Topological constraints on self-organisation in locally interacting systems","created":"2025-01-22","cited_by_count":0,"area":null},{"id":"2501.14846","title":"Wormhole Memory: A Rubik's Cube for Cross-Dialogue Retrieval","created":"2025-01-24","cited_by_count":0,"area":null},{"id":"2502.18009","title":"Patient Trajectory Prediction: Integrating Clinical Notes with Transformers","created":"2025-02-25","cited_by_count":0,"area":null},{"id":"2503.01564","title":"Attention Condensation via Sparsity Induced Regularized Training","created":"2025-03-03","cited_by_count":0,"area":null},{"id":"2506.11498","title":"Lag-Relative Sparse Attention In Long Context Training","created":"2025-06-13","cited_by_count":0,"area":null},{"id":"2601.06463","title":"Gecko: An Efficient Neural Architecture Inherently Processing Sequences with Arbitrary Lengths","created":"2026-01-10","cited_by_count":0,"area":null},{"id":"2602.07303","title":"KRONE: Scalable LLM-Augmented Log Anomaly Detection via Hierarchical Abstraction","created":"2026-02-07","cited_by_count":0,"area":null},{"id":"2603.00907","title":"KVSlimmer: Theoretical Insights and Practical Optimizations for Asymmetric KV Merging","created":"2026-03-01","cited_by_count":0,"area":null},{"id":"2604.11801","title":"CLSGen: A Dual-Head Fine-Tuning Framework for Joint Probabilistic Classification and Verbalized Explanation","created":"2026-04-13","cited_by_count":0,"area":null},{"id":"2604.15357","title":"Taming Asynchronous CPU-GPU Coupling for Frequency-aware Latency Estimation on Mobile Edge","created":"2026-04-11","cited_by_count":0,"area":null},{"id":"2609.35308","title":"Epistemic Policy Divergence in Multi-Turn LLM Contamination: A Protocol-Gradient Investigation","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.39661","title":"The Evolution of Attention in Large Language Models: Mechanisms, Trade-offs, and Emerging Trends","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.01230","title":"HHR: Hierarchical Hash Retrieval for Efficient LLM Generation","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.13735","title":"Orthros: Phase-Aware Heterogeneous Attention for Efficient Transformers","created":"2026-10-09","cited_by_count":0,"area":null}],"next_cursor":null}