{"total":1417,"rows":[{"id":"2309.17453","title":"Efficient Streaming Language Models with Attention Sinks","created":"2023-09-29","cited_by_count":2186,"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":"2404.14469","title":"SnapKV: LLM Knows What You are Looking for Before Generation","created":"2024-04-22","cited_by_count":880,"area":"inference"},{"id":"2402.02750","title":"KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache","created":"2024-02-05","cited_by_count":637,"area":"inference"},{"id":"2404.13501","title":"A Survey on the Memory Mechanism of Large Language Model based Agents","created":"2024-04-21","cited_by_count":634,"area":"wm"},{"id":"2401.18079","title":"KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization","created":"2024-01-31","cited_by_count":591,"area":"inference"},{"id":"2412.06464","title":"Gated Delta Networks: Improving Mamba2 with Delta Rule","created":"2024-12-09","cited_by_count":532,"area":null},{"id":"2508.06471","title":"GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models","created":"2025-08-08","cited_by_count":467,"area":"lr"},{"id":"2310.06839","title":"LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compression","created":"2023-10-10","cited_by_count":453,"area":"inference"},{"id":"2406.02069","title":"PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling","created":"2024-06-04","cited_by_count":432,"area":"inference"},{"id":"2502.11089","title":"Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention","created":"2025-02-16","cited_by_count":407,"area":null},{"id":"2412.15204","title":"LongBench v2: Towards Deeper Understanding and Reasoning on Realistic Long-context Multitasks","created":"2024-12-19","cited_by_count":379,"area":"lr"},{"id":"2402.13718","title":"$\\infty$Bench: Extending Long Context Evaluation Beyond 100K Tokens","created":"2024-02-21","cited_by_count":367,"area":null},{"id":"2403.12968","title":"LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression","created":"2024-03-19","cited_by_count":348,"area":"inference"},{"id":"2410.10819","title":"DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads","created":"2024-10-14","cited_by_count":288,"area":"inference"},{"id":"2311.04934","title":"Prompt Cache: Modular Attention Reuse for Low-Latency Inference","created":"2023-11-07","cited_by_count":268,"area":null},{"id":"2507.05257","title":"Evaluating Memory in LLM Agents via Incremental Multi-Turn Interactions","created":"2025-07-07","cited_by_count":254,"area":"agents"},{"id":"2507.02259","title":"MemAgent: Reshaping Long-Context LLM with Multi-Conv RL-based Memory Agent","created":"2025-07-03","cited_by_count":246,"area":"lr"},{"id":"2309.12307","title":"LongLoRA: Efficient Fine-tuning of Long-Context Large Language Models","created":"2023-09-21","cited_by_count":244,"area":null},{"id":"2407.11550","title":"Ada-KV: Optimizing KV Cache Eviction by Adaptive Budget Allocation for Efficient LLM Inference","created":"2024-07-16","cited_by_count":235,"area":"inference"},{"id":"2405.16444","title":"CacheBlend: Fast Large Language Model Serving for RAG with Cached Knowledge Fusion","created":"2024-05-26","cited_by_count":223,"area":"inference"},{"id":"2503.24235","title":"A Survey on Test-Time Scaling in Large Language Models: What, How, Where, and How Well?","created":"2025-03-31","cited_by_count":223,"area":"lr"},{"id":"2406.10149","title":"BABILong: Testing the Limits of LLMs with Long Context Reasoning-in-a-Haystack","created":"2024-06-14","cited_by_count":215,"area":"lr"},{"id":"2406.02818","title":"Chain of Agents: Large Language Models Collaborating on Long-Context Tasks","created":"2024-06-04","cited_by_count":206,"area":"agents"},{"id":"2310.19736","title":"Evaluating Large Language Models: A Comprehensive Survey","created":"2023-10-30","cited_by_count":202,"area":null},{"id":"2311.04939","title":"LooGLE: Can Long-Context Language Models Understand Long Contexts?","created":"2023-11-08","cited_by_count":202,"area":null},{"id":"2309.07045","title":"SafetyBench: Evaluating the Safety of Large Language Models","created":"2023-09-13","cited_by_count":199,"area":null},{"id":"2402.04617","title":"InfLLM: Training-Free Long-Context Extrapolation for LLMs with an Efficient Context Memory","created":"2024-02-07","cited_by_count":197,"area":"agents"},{"id":"2402.10171","title":"Data Engineering for Scaling Language Models to 128K Context","created":"2024-02-15","cited_by_count":186,"area":null},{"id":"2406.07887","title":"An Empirical Study of Mamba-based Language Models","created":"2024-06-12","cited_by_count":186,"area":"ssm"},{"id":"2407.01523","title":"MMLongBench-Doc: Benchmarking Long-context Document Understanding with Visualizations","created":"2024-07-01","cited_by_count":183,"area":null},{"id":"2504.14225","title":"Know Me, Respond to Me: Benchmarking LLMs for Dynamic User Profiling and Personalized Responses at Scale","created":"2025-04-19","cited_by_count":178,"area":null},{"id":"2506.06295","title":"dLLM-Cache: Accelerating Diffusion Large Language Models with Adaptive Caching","created":"2025-05-17","cited_by_count":169,"area":null},{"id":"2406.01721","title":"DuQuant: Distributing Outliers via Dual Transformation Makes Stronger Quantized LLMs","created":"2024-06-03","cited_by_count":167,"area":null},{"id":"2403.05527","title":"GEAR: An Efficient KV Cache Compression Recipe for Near-Lossless Generative Inference of LLM","created":"2024-03-08","cited_by_count":158,"area":"inference"},{"id":"2402.14848","title":"Same Task, More Tokens: the Impact of Input Length on the Reasoning Performance of Large Language Models","created":"2024-02-19","cited_by_count":152,"area":"lr"},{"id":"2502.09597","title":"Do LLMs Recognize Your Preferences? Evaluating Personalized Preference Following in LLMs","created":"2025-02-13","cited_by_count":148,"area":null},{"id":"2410.02660","title":"How to Train Long-Context Language Models (Effectively)","created":"2024-10-03","cited_by_count":146,"area":null},{"id":"2503.16428","title":"XAttention: Block Sparse Attention with Antidiagonal Scoring","created":"2025-03-20","cited_by_count":137,"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":"2602.06036","title":"DFlash: Block Diffusion for Flash Speculative Decoding","created":"2026-02-05","cited_by_count":135,"area":"diffusion"},{"id":"2410.21465","title":"ShadowKV: KV Cache in Shadows for High-Throughput Long-Context LLM Inference","created":"2024-10-28","cited_by_count":134,"area":"inference"},{"id":"2412.19442","title":"A Survey on Large Language Model Acceleration based on KV Cache Management","created":"2024-12-27","cited_by_count":131,"area":"lr"},{"id":"2403.09054","title":"Keyformer: KV Cache Reduction through Key Tokens Selection for Efficient Generative Inference","created":"2024-03-14","cited_by_count":126,"area":"inference"},{"id":"2502.05167","title":"NoLiMa: Long-Context Evaluation Beyond Literal Matching","created":"2025-02-07","cited_by_count":126,"area":null},{"id":"2510.09665","title":"LMCache: An Efficient KV Cache Layer for Enterprise-Scale LLM Inference","created":"2025-10-08","cited_by_count":126,"area":"inference"},{"id":"2405.14366","title":"MiniCache: KV Cache Compression in Depth Dimension for Large Language Models","created":"2024-05-23","cited_by_count":125,"area":"inference"},{"id":"2410.02694","title":"HELMET: How to Evaluate Long-Context Language Models Effectively and Thoroughly","created":"2024-10-03","cited_by_count":125,"area":null},{"id":"2504.19874","title":"TurboQuant: Online Vector Quantization with Near-optimal Distortion Rate","created":"2025-04-28","cited_by_count":125,"area":null},{"id":"2308.16137","title":"LM-Infinite: Zero-Shot Extreme Length Generalization for Large Language Models","created":"2023-08-30","cited_by_count":124,"area":null},{"id":"2410.13276","title":"SeerAttention: Learning Intrinsic Sparse Attention in Your LLMs","created":"2024-10-17","cited_by_count":124,"area":"moe"},{"id":"2502.20766","title":"FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference","created":"2025-02-28","cited_by_count":123,"area":null},{"id":"2406.17419","title":"Leave No Document Behind: Benchmarking Long-Context LLMs with Extended Multi-Doc QA","created":"2024-06-25","cited_by_count":122,"area":null},{"id":"2502.18137","title":"SpargeAttention: Accurate and Training-free Sparse Attention Accelerating Any Model Inference","created":"2025-02-25","cited_by_count":120,"area":null},{"id":"2404.16811","title":"Make Your LLM Fully Utilize the Context","created":"2024-04-25","cited_by_count":119,"area":null},{"id":"2406.10252","title":"AutoSurvey: Large Language Models Can Automatically Write Surveys","created":"2024-06-10","cited_by_count":119,"area":null},{"id":"2407.16833","title":"Retrieval Augmented Generation or Long-Context LLMs? A Comprehensive Study and Hybrid Approach","created":"2024-07-23","cited_by_count":119,"area":"rag"},{"id":"2409.05591","title":"MemoRAG: Boosting Long Context Processing with Global Memory-Enhanced Retrieval Augmentation","created":"2024-09-09","cited_by_count":119,"area":"rag"},{"id":"2310.03025","title":"Retrieval meets Long Context Large Language Models","created":"2023-10-04","cited_by_count":115,"area":null},{"id":"2411.10958","title":"SageAttention2: Efficient Attention with Thorough Outlier Smoothing and Per-thread INT4 Quantization","created":"2024-11-17","cited_by_count":114,"area":null},{"id":"2502.02533","title":"Multi-Agent Design: Optimizing Agents with Better Prompts and Topologies","created":"2025-02-04","cited_by_count":113,"area":"agents"},{"id":"2410.16179","title":"MagicPIG: LSH Sampling for Efficient LLM Generation","created":"2024-10-21","cited_by_count":111,"area":null},{"id":"2406.15319","title":"LongRAG: Enhancing Retrieval-Augmented Generation with Long-context LLMs","created":"2024-06-21","cited_by_count":108,"area":"rag"},{"id":"2401.18058","title":"LongAlign: A Recipe for Long Context Alignment of Large Language Models","created":"2024-01-31","cited_by_count":106,"area":"alignment"},{"id":"2401.03462","title":"Long Context Compression with Activation Beacon","created":"2024-01-07","cited_by_count":104,"area":"inference"},{"id":"2401.04259","title":"MARG: Multi-Agent Review Generation for Scientific Papers","created":"2024-01-08","cited_by_count":104,"area":"agents"},{"id":"2312.15234","title":"Towards Efficient Generative Large Language Model Serving: A Survey from Algorithms to Systems","created":"2023-12-23","cited_by_count":102,"area":"inference"},{"id":"2407.18003","title":"Keep the Cost Down: A Review on Methods to Optimize LLM' s KV-Cache Consumption","created":"2024-07-25","cited_by_count":97,"area":"inference"},{"id":"2410.19258","title":"Not All Heads Matter: A Head-Level KV Cache Compression Method with Integrated Retrieval and Reasoning","created":"2024-10-25","cited_by_count":97,"area":"lr"},{"id":"2407.08454","title":"Model Tells You Where to Merge: Adaptive KV Cache Merging for LLMs on Long-Context Tasks","created":"2024-07-11","cited_by_count":96,"area":"inference"},{"id":"2407.12820","title":"PQCache: Product Quantization-based KVCache for Long Context LLM Inference","created":"2024-07-01","cited_by_count":95,"area":"inference"},{"id":"2505.23416","title":"KVzip: Query-Agnostic KV Cache Compression with Context Reconstruction","created":"2025-05-29","cited_by_count":95,"area":"inference"},{"id":"2402.04624","title":"MEMORYLLM: Towards Self-Updatable Large Language Models","created":"2024-02-07","cited_by_count":93,"area":null},{"id":"2406.02542","title":"Loki: Low-rank Keys for Efficient Sparse Attention","created":"2024-06-04","cited_by_count":89,"area":null},{"id":"2409.12640","title":"Michelangelo: Long Context Evaluations Beyond Haystacks via Latent Structure Queries","created":"2024-09-19","cited_by_count":88,"area":"lr"},{"id":"2407.01370","title":"Summary of a Haystack: A Challenge to Long-Context LLMs and RAG Systems","created":"2024-07-01","cited_by_count":87,"area":"rag"},{"id":"2310.05869","title":"HyperAttention: Long-context Attention in Near-Linear Time","created":"2023-10-09","cited_by_count":85,"area":null},{"id":"2506.21605","title":"MemBench: Towards More Comprehensive Evaluation on the Memory of LLM-based Agents","created":"2025-06-20","cited_by_count":84,"area":"agents"},{"id":"2602.16313","title":"MemoryArena: Benchmarking Agent Memory in Interdependent Multi-Session Agentic Tasks","created":"2026-02-18","cited_by_count":84,"area":"agents"},{"id":"2402.05136","title":"LV-Eval: A Balanced Long-Context Benchmark with 5 Length Levels Up to 256K","created":"2024-02-06","cited_by_count":81,"area":null},{"id":"2409.02897","title":"LongCite: Enabling LLMs to Generate Fine-grained Citations in Long-context QA","created":"2024-09-04","cited_by_count":81,"area":null},{"id":"2406.16264","title":"One Thousand and One Pairs: A \"novel\" challenge for long-context language models","created":"2024-06-24","cited_by_count":80,"area":null},{"id":"2405.03917","title":"KV Cache is 1 Bit Per Channel: Efficient Large Language Model Inference with Coupled Quantization","created":"2024-05-07","cited_by_count":76,"area":"inference"},{"id":"2510.00636","title":"Expected Attention: KV Cache Compression by Estimating Attention from Future Queries Distribution","created":"2025-10-01","cited_by_count":74,"area":"inference"},{"id":"2401.02669","title":"Infinite-LLM: Efficient LLM Service for Long Context with DistAttention and Distributed KVCache","created":"2024-01-05","cited_by_count":73,"area":"inference"},{"id":"2406.12335","title":"Attention Score is not All You Need for Token Importance Indicator in KV Cache Reduction: Value Also Matters","created":"2024-06-18","cited_by_count":73,"area":"inference"},{"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":"2403.04797","title":"Found in the Middle: How Language Models Use Long Contexts Better via Plug-and-Play Positional Encoding","created":"2024-03-05","cited_by_count":72,"area":null},{"id":"2407.14057","title":"LazyLLM: Dynamic Token Pruning for Efficient Long Context LLM Inference","created":"2024-07-19","cited_by_count":70,"area":"inference"},{"id":"2402.12065","title":"WKVQuant: Quantizing Weight and Key/Value Cache for Large Language Models Gains More","created":"2024-02-19","cited_by_count":69,"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":"2311.18743","title":"AlignBench: Benchmarking Chinese Alignment of Large Language Models","created":"2023-11-30","cited_by_count":68,"area":"alignment"},{"id":"2407.21018","title":"ThinK: Thinner Key Cache by Query-Driven Pruning","created":"2024-07-30","cited_by_count":68,"area":"lr"},{"id":"2310.06762","title":"TRACE: A Comprehensive Benchmark for Continual Learning in Large Language Models","created":"2023-10-10","cited_by_count":66,"area":"alignment"},{"id":"2412.03213","title":"ClusterKV: Manipulating LLM KV Cache in Semantic Space for Recallable Compression","created":"2024-12-04","cited_by_count":65,"area":"lr"},{"id":"2310.07554","title":"A Multi-Task Embedder For Retrieval Augmented LLMs","created":"2023-10-11","cited_by_count":64,"area":"rag"},{"id":"2407.21118","title":"Palu: Compressing KV-Cache with Low-Rank Projection","created":"2024-07-30","cited_by_count":64,"area":"inference"},{"id":"2410.07590","title":"TurboRAG: Accelerating Retrieval-Augmented Generation with Precomputed KV Caches for Chunked Text","created":"2024-10-10","cited_by_count":63,"area":"rag"},{"id":"2407.05858","title":"Fast On-device LLM Inference with NPUs","created":"2024-07-08","cited_by_count":62,"area":null},{"id":"2407.09450","title":"Human-inspired Episodic Memory for Infinite Context LLMs","created":"2024-07-12","cited_by_count":62,"area":null}],"next_cursor":"100"}