{"total":84,"rows":[{"id":"2309.07864","title":"The Rise and Potential of Large Language Model Based Agents: A Survey","created":"2023-09-14","cited_by_count":1439,"area":"agents"},{"id":"2308.14508","title":"LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding","created":"2023-08-28","cited_by_count":1417,"area":null},{"id":"2306.14048","title":"H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models","created":"2023-06-24","cited_by_count":832,"area":"inference"},{"id":"2306.15595","title":"Extending Context Window of Large Language Models via Positional Interpolation","created":"2023-06-27","cited_by_count":740,"area":null},{"id":"2307.06435","title":"A Comprehensive Overview of Large Language Models","created":"2023-07-12","cited_by_count":648,"area":null},{"id":"2401.18059","title":"RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval","created":"2024-01-31","cited_by_count":532,"area":"rag"},{"id":"2310.07820","title":"Large Language Models Are Zero-Shot Time Series Forecasters","created":"2023-10-11","cited_by_count":500,"area":null},{"id":"2305.14788","title":"Adapting Language Models to Compress Contexts","created":"2023-05-24","cited_by_count":356,"area":null},{"id":"2306.03091","title":"RepoBench: Benchmarking Repository-Level Code Auto-Completion Systems","created":"2023-06-05","cited_by_count":353,"area":null},{"id":"2307.12856","title":"A Real-World WebAgent with Planning, Long Context Understanding, and Program Synthesis","created":"2023-07-24","cited_by_count":353,"area":null},{"id":"2307.10169","title":"Challenges and Applications of Large Language Models","created":"2023-07-19","cited_by_count":254,"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":"2502.13189","title":"MoBA: Mixture of Block Attention for Long-Context LLMs","created":"2025-02-18","cited_by_count":198,"area":"moe"},{"id":"2510.26692","title":"Kimi Linear: An Expressive, Efficient Attention Architecture","created":"2025-10-30","cited_by_count":196,"area":"deeprl"},{"id":"2305.13707","title":"Do All Languages Cost the Same? Tokenization in the Era of Commercial Language Models","created":"2023-05-23","cited_by_count":192,"area":null},{"id":"2309.13638","title":"Embers of Autoregression: Understanding Large Language Models Through the Problem They are Trained to Solve","created":"2023-09-24","cited_by_count":178,"area":null},{"id":"2305.14196","title":"ZeroSCROLLS: A Zero-Shot Benchmark for Long Text Understanding","created":"2023-05-23","cited_by_count":176,"area":null},{"id":"2307.03170","title":"Focused Transformer: Contrastive Training for Context Scaling","created":"2023-07-06","cited_by_count":133,"area":null},{"id":"2310.05029","title":"Walking Down the Memory Maze: Beyond Context Limit through Interactive Reading","created":"2023-10-08","cited_by_count":133,"area":null},{"id":"2402.12374","title":"Sequoia: Scalable, Robust, and Hardware-aware Speculative Decoding","created":"2024-02-19","cited_by_count":103,"area":"inference"},{"id":"2304.11062","title":"Scaling Transformer to 1M tokens and beyond with RMT","created":"2023-04-19","cited_by_count":98,"area":null},{"id":"2304.04947","title":"Conditional Adapters: Parameter-efficient Transfer Learning with Fast Inference","created":"2023-04-11","cited_by_count":69,"area":null},{"id":"2406.16747","title":"Sparser is Faster and Less is More: Efficient Sparse Attention for Long-Range Transformers","created":"2024-06-24","cited_by_count":52,"area":null},{"id":"2405.08944","title":"Challenges in Deploying Long-Context Transformers: A Theoretical Peak Performance Analysis","created":"2024-05-14","cited_by_count":44,"area":"agents"},{"id":"2307.06440","title":"No Train No Gain: Revisiting Efficient Training Algorithms For Transformer-based Language Models","created":"2023-07-12","cited_by_count":41,"area":null},{"id":"2401.07872","title":"The What, Why, and How of Context Length Extension Techniques in Large Language Models -- A Detailed Survey","created":"2024-01-15","cited_by_count":33,"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":"2503.23798","title":"Adaptive Layer-skipping in Pre-trained LLMs","created":"2025-03-31","cited_by_count":27,"area":null},{"id":"2505.18962","title":"System-1.5 Reasoning: Traversal in Language and Latent Spaces with Dynamic Shortcuts","created":"2025-05-25","cited_by_count":27,"area":"lr"},{"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":"2305.14879","title":"ByteSized32: A Corpus and Challenge Task for Generating Task-Specific World Models Expressed as Text Games","created":"2023-05-24","cited_by_count":23,"area":"wm"},{"id":"2310.02409","title":"Dodo: Dynamic Contextual Compression for Decoder-only LMs","created":"2023-10-03","cited_by_count":23,"area":null},{"id":"2401.03411","title":"GRAM: Global Reasoning for Multi-Page VQA","created":"2024-01-07","cited_by_count":23,"area":"lr"},{"id":"2510.05520","title":"CAM: A Constructivist View of Agentic Memory for LLM-Based Reading Comprehension","created":"2025-10-07","cited_by_count":23,"area":"agents"},{"id":"2311.15436","title":"Learning to Skip for Language Modeling","created":"2023-11-26","cited_by_count":19,"area":null},{"id":"2503.10337","title":"KV-Distill: Nearly Lossless Learnable Context Compression for LLMs","created":"2025-03-13","cited_by_count":19,"area":"inference"},{"id":"2310.04418","title":"Functional Interpolation for Relative Positions Improves Long Context Transformers","created":"2023-10-06","cited_by_count":18,"area":null},{"id":"2501.02086","title":"Instruction-Following Pruning for Large Language Models","created":"2025-01-03","cited_by_count":17,"area":null},{"id":"2407.14093","title":"Routing Experts: Learning to Route Dynamic Experts in Multi-modal Large Language Models","created":"2024-07-19","cited_by_count":14,"area":"mllm"},{"id":"2311.05720","title":"Long-Horizon Dialogue Understanding for Role Identification in the Game of Avalon with Large Language Models","created":"2023-11-09","cited_by_count":12,"area":null},{"id":"2407.06677","title":"Mixture-of-Modules: Reinventing Transformers as Dynamic Assemblies of Modules","created":"2024-07-09","cited_by_count":11,"area":null},{"id":"2310.13682","title":"Optimizing Retrieval-augmented Reader Models via Token Elimination","created":"2023-10-20","cited_by_count":10,"area":"rag"},{"id":"2403.07965","title":"Conditional computation in neural networks: principles and research trends","created":"2024-03-12","cited_by_count":10,"area":"moe"},{"id":"2407.11030","title":"DLO: Dynamic Layer Operation for Efficient Vertical Scaling of LLMs","created":"2024-07-03","cited_by_count":10,"area":"moe"},{"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":"2410.23463","title":"MDCure: A Scalable Pipeline for Multi-Document Instruction-Following","created":"2024-10-30","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":"2606.04438","title":"LoopMoE: Unifying Iterative Computation with Mixture-of-Experts for Language Modeling","created":"2026-06-03","cited_by_count":10,"area":"moe"},{"id":"2308.13191","title":"Chunk, Align, Select: A Simple Long-sequence Processing Method for Transformers","created":"2023-08-25","cited_by_count":9,"area":null},{"id":"2311.13565","title":"Drilling Down into the Discourse Structure with LLMs for Long Document Question Answering","created":"2023-11-22","cited_by_count":8,"area":null},{"id":"2505.19959","title":"MiniLongBench: The Low-cost Long Context Understanding Benchmark for Large Language Models","created":"2025-05-26","cited_by_count":8,"area":null},{"id":"2306.10231","title":"GLIMMER: generalized late-interaction memory reranker","created":"2023-06-17","cited_by_count":7,"area":null},{"id":"2410.09454","title":"Skipping Computations in Multimodal LLMs","created":"2024-10-12","cited_by_count":7,"area":"mllm"},{"id":"2312.10193","title":"Adaptive Computation Modules: Granular Conditional Computation For Efficient Inference","created":"2023-12-15","cited_by_count":6,"area":null},{"id":"2406.13167","title":"QRMeM: Unleash the Length Limitation through Question then Reflection Memory Mechanism","created":"2024-06-19","cited_by_count":6,"area":null},{"id":"2407.08330","title":"HDT: Hierarchical Document Transformer","created":"2024-07-11","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":"2506.06644","title":"Spark Transformer: Reactivating Sparsity in FFN and Attention","created":"2025-06-07","cited_by_count":5,"area":null},{"id":"2408.15491","title":"Enhancing and Accelerating Large Language Models via Instruction-Aware Contextual Compression","created":"2024-08-28","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":"2604.07012","title":"DTCRS: Dynamic Tree Construction for Recursive Summarization","created":"2026-04-08","cited_by_count":4,"area":"rag"},{"id":"2502.18277","title":"Self-Adjust Softmax","created":"2025-02-25","cited_by_count":3,"area":null},{"id":"2504.06426","title":"S'MoRE: Structural Mixture of Residual Experts for Parameter-Efficient LLM Fine-tuning","created":"2025-04-08","cited_by_count":3,"area":"moe"},{"id":"2509.25689","title":"Collaborative Compression for Large-Scale MoE Deployment on Edge","created":"2025-09-30","cited_by_count":3,"area":"moe"},{"id":"2510.20787","title":"Alleviating Forgetfulness of Linear Attention by Hybrid Sparse Attention and Contextualized Learnable Token Eviction","created":"2025-10-23","cited_by_count":3,"area":"inference"},{"id":"2603.11535","title":"Expert Threshold Routing for Autoregressive Language Modeling with Dynamic Computation Allocation and Load Balancing","created":"2026-03-12","cited_by_count":3,"area":"moe"},{"id":"2406.10985","title":"Taking a Deep Breath: Enhancing Language Modeling of Large Language Models with Sentinel Tokens","created":"2024-06-16","cited_by_count":2,"area":null},{"id":"2510.13161","title":"Mirror Speculative Decoding: Breaking the Serial Barrier in LLM Inference","created":"2025-10-15","cited_by_count":2,"area":"inference"},{"id":"2310.07911","title":"Pit One Against Many: Leveraging Attention-head Embeddings for Parameter-efficient Multi-head Attention","created":"2023-10-11","cited_by_count":1,"area":null},{"id":"2502.02040","title":"M2R2: Mixture of Multi-Rate Residuals for Efficient Transformer Inference","created":"2025-02-04","cited_by_count":1,"area":"moe"},{"id":"2503.17279","title":"CASE -- Condition-Aware Sentence Embeddings for Conditional Semantic Textual Similarity Measurement","created":"2025-03-21","cited_by_count":1,"area":null},{"id":"2512.22562","title":"Learning When Not to Attend Globally","created":"2025-12-27","cited_by_count":1,"area":null},{"id":"2601.02569","title":"LoRA-Drop: Temporal LoRA Decoding for Efficient LLM Inference","created":"2026-01-05","cited_by_count":1,"area":"inference"},{"id":"2608.29539","title":"LoGo: Token-Level Dynamic Local-Global Attention","created":"2026-08-30","cited_by_count":1,"area":null},{"id":"2610.03198","title":"KV$^2$: A Self-Refining KV Cache","created":"2026-10-02","cited_by_count":1,"area":"inference"},{"id":"2308.11199","title":"ConcatPlexer: Additional Dim1 Batching for Faster ViTs","created":"2023-08-22","cited_by_count":0,"area":null},{"id":"2311.01326","title":"Better Together: Enhancing Generative Knowledge Graph Completion with Language Models and Neighborhood Information","created":"2023-11-02","cited_by_count":0,"area":null},{"id":"2406.06571","title":"SUBLLM: A Novel Efficient Architecture with Token Sequence Subsampling for LLM","created":"2024-06-03","cited_by_count":0,"area":null},{"id":"2509.24074","title":"ResFormer: All-Time Reservoir Memory for Long Sequence Classification","created":"2025-09-28","cited_by_count":0,"area":null},{"id":"2510.01585","title":"ReSSFormer: A Recursive Sparse Structured Transformer for Scalable and Long-Context Reasoning","created":"2025-10-02","cited_by_count":0,"area":"lr"},{"id":"2606.14695","title":"Persona-Pruner: Sculpting Lightweight Models for Role-Playing","created":"2026-06-12","cited_by_count":0,"area":null},{"id":"2607.06601","title":"TriRoute: Unified Learned Routing for Joint Adaptive Attention, Experts, and KV-Cache Allocation","created":"2026-07-07","cited_by_count":0,"area":"moe"},{"id":"2608.21174","title":"From Attention Masks to Inert Zero-Vector Tokens: OAttention and O-Closure for Token Dynamics","created":"2026-08-21","cited_by_count":0,"area":null},{"id":"2609.20734","title":"On-Demand Attention: Language Models Know When to Recall","created":"2026-09-17","cited_by_count":0,"area":"agents"}],"next_cursor":null}