{"list":"other","total":69,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2505.09388","title":"Qwen3 Technical Report","created":"2025-05-14","cited_by_count":8820},{"id":"2312.00752","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","created":"2023-12-01","cited_by_count":4718},{"id":"2104.09864","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","created":"2021-04-20","cited_by_count":4703},{"id":"2507.06261","title":"Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities","created":"2025-07-07","cited_by_count":3796},{"id":"1809.09600","title":"HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering","created":"2018-09-25","cited_by_count":3754},{"id":"2205.14135","title":"FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness","created":"2022-05-27","cited_by_count":3673},{"id":"2307.03172","title":"Lost in the Middle: How Language Models Use Long Contexts","created":"2023-07-06","cited_by_count":3455},{"id":"2203.15556","title":"Training Compute-Optimal Large Language Models","created":"2022-03-29","cited_by_count":3019},{"id":"1904.09751","title":"The Curious Case of Neural Text Degeneration","created":"2019-04-22","cited_by_count":2916},{"id":"2307.08691","title":"FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning","created":"2023-07-17","cited_by_count":2598},{"id":"2309.17453","title":"Efficient Streaming Language Models with Attention Sinks","created":"2023-09-29","cited_by_count":2186},{"id":"2308.14508","title":"LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding","created":"2023-08-28","cited_by_count":1417},{"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},{"id":"2104.08663","title":"BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models","created":"2021-04-17","cited_by_count":1252},{"id":"2404.14469","title":"SnapKV: LLM Knows What You are Looking for Before Generation","created":"2024-04-22","cited_by_count":880},{"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},{"id":"2305.13048","title":"RWKV: Reinventing RNNs for the Transformer Era","created":"2023-05-22","cited_by_count":827},{"id":"2306.15595","title":"Extending Context Window of Large Language Models via Positional Interpolation","created":"2023-06-27","cited_by_count":740},{"id":"2309.00071","title":"YaRN: Efficient Context Window Extension of Large Language Models","created":"2023-08-31","cited_by_count":601},{"id":"2310.06839","title":"LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compression","created":"2023-10-10","cited_by_count":453},{"id":"2403.19887","title":"Jamba: A Hybrid Transformer-Mamba Language Model","created":"2024-03-28","cited_by_count":401},{"id":"2407.02490","title":"MInference 1.0: Accelerating Pre-filling for Long-Context LLMs via Dynamic Sparse Attention","created":"2024-07-02","cited_by_count":383},{"id":"2412.15204","title":"LongBench v2: Towards Deeper Understanding and Reasoning on Realistic Long-context Multitasks","created":"2024-12-19","cited_by_count":379},{"id":"2402.13718","title":"$\\infty$Bench: Extending Long Context Evaluation Beyond 100K Tokens","created":"2024-02-21","cited_by_count":367},{"id":"2410.10819","title":"DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads","created":"2024-10-14","cited_by_count":288},{"id":"2309.12307","title":"LongLoRA: Efficient Fine-tuning of Long-Context Large Language Models","created":"2023-09-21","cited_by_count":244},{"id":"2404.15574","title":"Retrieval Head Mechanistically Explains Long-Context Factuality","created":"2024-04-24","cited_by_count":232},{"id":"2406.02818","title":"Chain of Agents: Large Language Models Collaborating on Long-Context Tasks","created":"2024-06-04","cited_by_count":206},{"id":"2402.10171","title":"Data Engineering for Scaling Language Models to 128K Context","created":"2024-02-15","cited_by_count":186},{"id":"2410.02660","title":"How to Train Long-Context Language Models (Effectively)","created":"2024-10-03","cited_by_count":146},{"id":"2408.07055","title":"LongWriter: Unleashing 10,000+ Word Generation from Long Context LLMs","created":"2024-08-13","cited_by_count":144},{"id":"2509.13313","title":"ReSum: Unlocking Long-Horizon Search Intelligence via Context Summarization","created":"2025-09-16","cited_by_count":141},{"id":"2401.01325","title":"LLM Maybe LongLM: Self-Extend LLM Context Window Without Tuning","created":"2024-01-02","cited_by_count":136},{"id":"2310.05029","title":"Walking Down the Memory Maze: Beyond Context Limit through Interactive Reading","created":"2023-10-08","cited_by_count":133},{"id":"2305.01625","title":"Unlimiformer: Long-Range Transformers with Unlimited Length Input","created":"2023-05-02","cited_by_count":128},{"id":"2404.16811","title":"Make Your LLM Fully Utilize the Context","created":"2024-04-25","cited_by_count":119},{"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},{"id":"2412.19048","title":"Jasper and Stella: distillation of SOTA embedding models","created":"2024-12-26","cited_by_count":112},{"id":"2309.10400","title":"PoSE: Efficient Context Window Extension of LLMs via Positional Skip-wise Training","created":"2023-09-19","cited_by_count":111},{"id":"2512.24601","title":"Recursive Language Models","created":"2025-12-31","cited_by_count":104},{"id":"2406.16008","title":"Found in the Middle: Calibrating Positional Attention Bias Improves Long Context Utilization","created":"2024-06-23","cited_by_count":101},{"id":"2409.12640","title":"Michelangelo: Long Context Evaluations Beyond Haystacks via Latent Structure Queries","created":"2024-09-19","cited_by_count":88},{"id":"2402.16617","title":"Long-Context Language Modeling with Parallel Context Encoding","created":"2024-02-26","cited_by_count":84},{"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},{"id":"2406.01563","title":"LoFiT: Localized Fine-tuning on LLM Representations","created":"2024-06-03","cited_by_count":57},{"id":"2410.18050","title":"LongRAG: A Dual-Perspective Retrieval-Augmented Generation Paradigm for Long-Context Question Answering","created":"2024-10-23","cited_by_count":49},{"id":"2409.02076","title":"LongGenBench: Benchmarking Long-Form Generation in Long Context LLMs","created":"2024-09-03","cited_by_count":47},{"id":"2501.19399","title":"Scalable-Softmax Is Superior for Attention","created":"2025-01-31","cited_by_count":45},{"id":"2406.14673","title":"Insights into LLM Long-Context Failures: When Transformers Know but Don't Tell","created":"2024-06-20","cited_by_count":36},{"id":"2403.12766","title":"NovelQA: Benchmarking Question Answering on Documents Exceeding 200K Tokens","created":"2024-03-18","cited_by_count":32},{"id":"2506.09944","title":"Query-Focused Retrieval Heads Improve Long-Context Reasoning and Re-ranking","created":"2025-06-11","cited_by_count":31},{"id":"2501.05414","title":"LongProc: Benchmarking Long-Context Language Models on Long Procedural Generation","created":"2025-01-09","cited_by_count":29},{"id":"2410.04199","title":"LongGenBench: Long-context Generation Benchmark","created":"2024-10-05","cited_by_count":28},{"id":"2407.00402","title":"Is It Really Long Context if All You Need Is Retrieval? Towards Genuinely Difficult Long Context NLP","created":"2024-06-29","cited_by_count":27},{"id":"2410.01518","title":"InfiniPot: Infinite Context Processing on Memory-Constrained LLMs","created":"2024-10-02","cited_by_count":27},{"id":"2502.13922","title":"LongPO: Long Context Self-Evolution of Large Language Models through Short-to-Long Preference Optimization","created":"2025-02-19","cited_by_count":24},{"id":"2409.00509","title":"LongRecipe: Recipe for Efficient Long Context Generalization in Large Language Models","created":"2024-08-31","cited_by_count":23},{"id":"2501.12766","title":"NExtLong: Toward Effective Long-Context Training without Long Documents","created":"2025-01-22","cited_by_count":20},{"id":"2510.05554","title":"Critical attention scaling in long-context transformers","created":"2025-10-07","cited_by_count":20},{"id":"2512.13898","title":"Let's (not) just put things in Context: Test-Time Training for Long-Context LLMs","created":"2025-12-15","cited_by_count":18},{"id":"2501.08248","title":"Eliciting In-context Retrieval and Reasoning for Long-context Large Language Models","created":"2025-01-14","cited_by_count":11},{"id":"2503.02502","title":"LADM: Long-context Training Data Selection with Attention-based Dependency Measurement for LLMs","created":"2025-03-04","cited_by_count":11},{"id":"2410.22316","title":"Understanding Synthetic Context Extension via Retrieval Heads","created":"2024-10-29","cited_by_count":10},{"id":"2502.14854","title":"CLIPPER: Compression enables long-context synthetic data generation","created":"2025-02-20","cited_by_count":10},{"id":"2503.23306","title":"Focus Directions Make Your Language Models Pay More Attention to Relevant Contexts","created":"2025-03-30","cited_by_count":9},{"id":"2507.06415","title":"PERK: Long-Context Reasoning as Test-Time Learning","created":"2025-07-08","cited_by_count":4},{"id":"2502.13963","title":"MuDAF: Long-Context Multi-Document Attention Focusing through Contrastive Learning on Attention Heads","created":"2025-02-19","cited_by_count":3}],"next_cursor":null}