{"list":"other","total":51,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2104.09864","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","created":"2021-04-20","cited_by_count":4703},{"id":"1905.07830","title":"HellaSwag: Can a Machine Really Finish Your Sentence?","created":"2019-05-19","cited_by_count":4100},{"id":"2310.06770","title":"SWE-bench: Can Language Models Resolve Real-World GitHub Issues?","created":"2023-10-10","cited_by_count":3373},{"id":"2310.06825","title":"Mistral 7B","created":"2023-10-10","cited_by_count":3164},{"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":"2404.14219","title":"Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone","created":"2024-04-22","cited_by_count":1917},{"id":"2305.13245","title":"GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints","created":"2023-05-22","cited_by_count":1346},{"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":"1803.02155","title":"Self-Attention with Relative Position Representations","created":"2018-03-06","cited_by_count":1120},{"id":"2306.15595","title":"Extending Context Window of Large Language Models via Positional Interpolation","created":"2023-06-27","cited_by_count":740},{"id":"2008.02275","title":"Aligning AI With Shared Human Values","created":"2020-08-05","cited_by_count":723},{"id":"2309.00071","title":"YaRN: Efficient Context Window Extension of Large Language Models","created":"2023-08-31","cited_by_count":601},{"id":"2310.01889","title":"Ring Attention with Blockwise Transformers for Near-Infinite Context","created":"2023-10-03","cited_by_count":457},{"id":"2402.13718","title":"$\\infty$Bench: Extending Long Context Evaluation Beyond 100K Tokens","created":"2024-02-21","cited_by_count":367},{"id":"2309.16039","title":"Effective Long-Context Scaling of Foundation Models","created":"2023-09-27","cited_by_count":303},{"id":"2402.17762","title":"Massive Activations in Large Language Models","created":"2024-02-27","cited_by_count":294},{"id":"2309.14509","title":"DeepSpeed Ulysses: System Optimizations for Enabling Training of Extreme Long Sequence Transformer Models","created":"2023-09-25","cited_by_count":245},{"id":"2309.12307","title":"LongLoRA: Efficient Fine-tuning of Long-Context Large Language Models","created":"2023-09-21","cited_by_count":244},{"id":"1905.12322","title":"A Study of BFLOAT16 for Deep Learning Training","created":"2019-05-29","cited_by_count":232},{"id":"2410.10781","title":"When Attention Sink Emerges in Language Models: An Empirical View","created":"2024-10-14","cited_by_count":208},{"id":"2404.11018","title":"Many-Shot In-Context Learning","created":"2024-04-17","cited_by_count":206},{"id":"2006.15595","title":"Rethinking Positional Encoding in Language Pre-training","created":"2020-06-28","cited_by_count":197},{"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":"2404.05405","title":"Physics of Language Models: Part 3.3, Knowledge Capacity Scaling Laws","created":"2024-04-08","cited_by_count":144},{"id":"2401.01325","title":"LLM Maybe LongLM: Self-Extend LLM Context Window Without Tuning","created":"2024-01-02","cited_by_count":136},{"id":"2305.01625","title":"Unlimiformer: Long-Range Transformers with Unlimited Length Input","created":"2023-05-02","cited_by_count":128},{"id":"2105.13120","title":"Sequence Parallelism: Long Sequence Training from System Perspective","created":"2021-05-26","cited_by_count":126},{"id":"2310.05209","title":"Scaling Laws of RoPE-based Extrapolation","created":"2023-10-08","cited_by_count":125},{"id":"2410.02694","title":"HELMET: How to Evaluate Long-Context Language Models Effectively and Thoroughly","created":"2024-10-03","cited_by_count":125},{"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},{"id":"2305.16843","title":"Randomized Positional Encodings Boost Length Generalization of Transformers","created":"2023-05-26","cited_by_count":117},{"id":"2409.02897","title":"LongCite: Enabling LLMs to Generate Fine-grained Citations in Long-context QA","created":"2024-09-04","cited_by_count":81},{"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},{"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},{"id":"2410.23771","title":"What is Wrong with Perplexity for Long-context Language Modeling?","created":"2024-10-31","cited_by_count":69},{"id":"2410.13835","title":"Active-Dormant Attention Heads: Mechanistically Demystifying Extreme-Token Phenomena in LLMs","created":"2024-10-17","cited_by_count":56},{"id":"2405.14591","title":"Base of RoPE Bounds Context Length","created":"2024-05-23","cited_by_count":52},{"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},{"id":"2405.06105","title":"Can Perplexity Reflect Large Language Model's Ability in Long Text Understanding?","created":"2024-05-09","cited_by_count":45},{"id":"2310.16450","title":"CLEX: Continuous Length Extrapolation for Large Language Models","created":"2023-10-25","cited_by_count":44},{"id":"2403.00071","title":"Resonance RoPE: Improving Context Length Generalization of Large Language Models","created":"2024-02-29","cited_by_count":27},{"id":"2402.13991","title":"Analysing The Impact of Sequence Composition on Language Model Pre-Training","created":"2024-02-21","cited_by_count":25},{"id":"2402.04779","title":"StableMask: Refining Causal Masking in Decoder-only Transformer","created":"2024-02-07","cited_by_count":20},{"id":"2406.00605","title":"LongSkywork: A Training Recipe for Efficiently Extending Context Length in Large Language Models","created":"2024-06-02","cited_by_count":19},{"id":"2211.06553","title":"Lifelong and Continual Learning Dialogue Systems","created":"2022-11-12","cited_by_count":9},{"id":"2410.01485","title":"A Little Goes a Long Way: Efficient Long Context Training and Inference with Partial Contexts","created":"2024-10-02","cited_by_count":9},{"id":"2406.01976","title":"Conditional Language Learning with Context","created":"2024-06-04","cited_by_count":4}],"next_cursor":null}