{"list":"other","total":54,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2005.11401","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","created":"2020-05-22","cited_by_count":9297},{"id":"2309.06180","title":"Efficient Memory Management for Large Language Model Serving with PagedAttention","created":"2023-09-12","cited_by_count":5944},{"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":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"2304.03442","title":"Generative Agents: Interactive Simulacra of Human Behavior","created":"2023-04-07","cited_by_count":3568},{"id":"2307.03172","title":"Lost in the Middle: How Language Models Use Long Contexts","created":"2023-07-06","cited_by_count":3455},{"id":"2004.05150","title":"Longformer: The Long-Document Transformer","created":"2020-04-10","cited_by_count":3413},{"id":"2307.08691","title":"FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning","created":"2023-07-17","cited_by_count":2598},{"id":"2111.00396","title":"Efficiently Modeling Long Sequences with Structured State Spaces","created":"2021-10-31","cited_by_count":2465},{"id":"2308.11432","title":"A Survey on Large Language Model based Autonomous Agents","created":"2023-08-22","cited_by_count":2242},{"id":"2309.17453","title":"Efficient Streaming Language Models with Attention Sinks","created":"2023-09-29","cited_by_count":2186},{"id":"2303.03378","title":"PaLM-E: An Embodied Multimodal Language Model","created":"2023-03-06","cited_by_count":2071},{"id":"2006.16236","title":"Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention","created":"2020-06-29","cited_by_count":2022},{"id":"1901.02860","title":"Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context","created":"2019-01-09","cited_by_count":1850},{"id":"2112.09332","title":"WebGPT: Browser-assisted question-answering with human feedback","created":"2021-12-17","cited_by_count":1745},{"id":"2007.14062","title":"Big Bird: Transformers for Longer Sequences","created":"2020-07-28","cited_by_count":1684},{"id":"2001.04451","title":"Reformer: The Efficient Transformer","created":"2020-01-13","cited_by_count":1668},{"id":"1904.10509","title":"Generating Long Sequences with Sparse Transformers","created":"2019-04-23","cited_by_count":1546},{"id":"2006.04768","title":"Linformer: Self-Attention with Linear Complexity","created":"2020-06-08","cited_by_count":1474},{"id":"2308.14508","title":"LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding","created":"2023-08-28","cited_by_count":1417},{"id":"2209.07753","title":"Code as Policies: Language Model Programs for Embodied Control","created":"2022-09-16","cited_by_count":1210},{"id":"2108.12409","title":"Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation","created":"2021-08-27","cited_by_count":1103},{"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":"1911.00172","title":"Generalization through Memorization: Nearest Neighbor Language Models","created":"2019-11-01","cited_by_count":800},{"id":"2009.06732","title":"Efficient Transformers: A Survey","created":"2020-09-14","cited_by_count":790},{"id":"2306.15595","title":"Extending Context Window of Large Language Models via Positional Interpolation","created":"2023-06-27","cited_by_count":740},{"id":"1911.05507","title":"Compressive Transformers for Long-Range Sequence Modelling","created":"2019-11-13","cited_by_count":726},{"id":"1410.5401","title":"Neural Turing Machines","created":"2014-10-20","cited_by_count":644},{"id":"2210.07316","title":"MTEB: Massive Text Embedding Benchmark","created":"2022-10-13","cited_by_count":640},{"id":"2309.00071","title":"YaRN: Efficient Context Window Extension of Large Language Models","created":"2023-08-31","cited_by_count":601},{"id":"2310.01801","title":"Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs","created":"2023-10-03","cited_by_count":474},{"id":"1410.3916","title":"Memory Networks","created":"2014-10-15","cited_by_count":363},{"id":"2106.07139","title":"Pre-Trained Models: Past, Present and Future","created":"2021-06-14","cited_by_count":319},{"id":"2309.16039","title":"Effective Long-Context Scaling of Foundation Models","created":"2023-09-27","cited_by_count":303},{"id":"2401.00368","title":"Improving Text Embeddings with Large Language Models","created":"2023-12-31","cited_by_count":303},{"id":"1606.03126","title":"Key-Value Memory Networks for Directly Reading Documents","created":"2016-06-09","cited_by_count":223},{"id":"2305.16300","title":"Landmark Attention: Random-Access Infinite Context Length for Transformers","created":"2023-05-25","cited_by_count":213},{"id":"2006.03236","title":"Funnel-Transformer: Filtering out Sequential Redundancy for Efficient Language Processing","created":"2020-06-05","cited_by_count":162},{"id":"2401.01325","title":"LLM Maybe LongLM: Self-Extend LLM Context Window Without Tuning","created":"2024-01-02","cited_by_count":136},{"id":"2307.03170","title":"Focused Transformer: Contrastive Training for Context Scaling","created":"2023-07-06","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":"2212.10554","title":"A Length-Extrapolatable Transformer","created":"2022-12-20","cited_by_count":127},{"id":"2302.07452","title":"How to Train Your DRAGON: Diverse Augmentation Towards Generalizable Dense Retrieval","created":"2023-02-15","cited_by_count":118},{"id":"2310.03025","title":"Retrieval meets Long Context Large Language Models","created":"2023-10-04","cited_by_count":115},{"id":"2311.12351","title":"Advancing Transformer Architecture in Long-Context Large Language Models: A Comprehensive Survey","created":"2023-11-21","cited_by_count":72},{"id":"1912.11637","title":"Explicit Sparse Transformer: Concentrated Attention Through Explicit Selection","created":"2019-12-25","cited_by_count":62},{"id":"2302.14502","title":"A Survey on Long Text Modeling with Transformers","created":"2023-02-28","cited_by_count":47},{"id":"2310.16450","title":"CLEX: Continuous Length Extrapolation for Large Language Models","created":"2023-10-25","cited_by_count":44}],"next_cursor":null}