{"list":"other","total":60,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"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":"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":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"1702.08734","title":"Billion-scale similarity search with GPUs","created":"2017-02-28","cited_by_count":2497},{"id":"1510.00149","title":"Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding","created":"2015-10-01","cited_by_count":2329},{"id":"2012.07805","title":"Extracting Training Data from Large Language Models","created":"2020-12-14","cited_by_count":2189},{"id":"2002.08909","title":"REALM: Retrieval-Augmented Language Model Pre-Training","created":"2020-02-10","cited_by_count":2141},{"id":"2210.17323","title":"GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers","created":"2022-10-31","cited_by_count":1919},{"id":"1904.01038","title":"fairseq: A Fast, Extensible Toolkit for Sequence Modeling","created":"2019-04-01","cited_by_count":1488},{"id":"1910.02054","title":"ZeRO: Memory Optimizations Toward Training Trillion Parameter Models","created":"2019-10-04","cited_by_count":1301},{"id":"2112.04426","title":"Improving language models by retrieving from trillions of tokens","created":"2021-12-08","cited_by_count":1293},{"id":"2007.01282","title":"Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering","created":"2020-07-02","cited_by_count":1210},{"id":"2112.11446","title":"Scaling Language Models: Methods, Analysis & Insights from Training Gopher","created":"2021-12-08","cited_by_count":1202},{"id":"1912.03817","title":"Machine Unlearning","created":"2019-12-09","cited_by_count":1061},{"id":"2112.04359","title":"Ethical and social risks of harm from Language Models","created":"2021-12-08","cited_by_count":966},{"id":"2208.03299","title":"Atlas: Few-shot Learning with Retrieval Augmented Language Models","created":"2022-08-05","cited_by_count":952},{"id":"1603.09320","title":"Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphs","created":"2016-03-30","cited_by_count":861},{"id":"1911.00172","title":"Generalization through Memorization: Nearest Neighbor Language Models","created":"2019-11-01","cited_by_count":800},{"id":"2302.00083","title":"In-Context Retrieval-Augmented Language Models","created":"2023-01-31","cited_by_count":702},{"id":"1704.04760","title":"In-Datacenter Performance Analysis of a Tensor Processing Unit","created":"2017-04-16","cited_by_count":618},{"id":"2201.11990","title":"Using DeepSpeed and Megatron to Train Megatron-Turing NLG 530B, A Large-Scale Generative Language Model","created":"2022-01-28","cited_by_count":559},{"id":"2107.07566","title":"Internet-Augmented Dialogue Generation","created":"2021-07-15","cited_by_count":217},{"id":"2010.00710","title":"Nearest Neighbor Machine Translation","created":"2020-10-01","cited_by_count":209},{"id":"2005.02205","title":"When Machine Unlearning Jeopardizes Privacy","created":"2020-05-05","cited_by_count":198},{"id":"2007.00072","title":"Data Movement Is All You Need: A Case Study on Optimizing Transformers","created":"2020-06-30","cited_by_count":108},{"id":"1707.00143","title":"Fast Approximate Nearest Neighbor Search With The Navigating Spreading-out Graph","created":"2017-07-01","cited_by_count":104},{"id":"2203.13224","title":"Language Models that Seek for Knowledge: Modular Search & Generation for Dialogue and Prompt Completion","created":"2022-03-24","cited_by_count":102},{"id":"2002.10941","title":"A$^3$: Accelerating Attention Mechanisms in Neural Networks with Approximation","created":"2020-02-22","cited_by_count":101},{"id":"2006.15020","title":"Pre-training via Paraphrasing","created":"2020-06-26","cited_by_count":92},{"id":"2102.02557","title":"Adaptive Semiparametric Language Models","created":"2021-02-04","cited_by_count":83},{"id":"2101.00408","title":"End-to-End Training of Neural Retrievers for Open-Domain Question Answering","created":"2021-01-02","cited_by_count":75},{"id":"2201.12431","title":"Neuro-Symbolic Language Modeling with Automaton-augmented Retrieval","created":"2022-01-28","cited_by_count":60},{"id":"2310.07713","title":"InstructRetro: Instruction Tuning post Retrieval-Augmented Pretraining","created":"2023-10-11","cited_by_count":53},{"id":"2105.14528","title":"Fast Nearest Neighbor Machine Translation","created":"2021-05-30","cited_by_count":37},{"id":"2102.00075","title":"RecSSD: Near Data Processing for Solid State Drive Based Recommendation Inference","created":"2021-01-29","cited_by_count":35},{"id":"2111.08566","title":"SPANN: Highly-efficient Billion-scale Approximate Nearest Neighbor Search","created":"2021-11-05","cited_by_count":35},{"id":"2301.02828","title":"Why do Nearest Neighbor Language Models Work?","created":"2023-01-07","cited_by_count":29},{"id":"2303.09855","title":"High-Dimensional Approximate Nearest Neighbor Search: with Reliable and Efficient Distance Comparison Operations","created":"2023-03-17","cited_by_count":26},{"id":"2210.05758","title":"Decoupled Context Processing for Context Augmented Language Modeling","created":"2022-10-11","cited_by_count":24},{"id":"2304.14347","title":"The Dark Side of ChatGPT: Legal and Ethical Challenges from Stochastic Parrots and Hallucination","created":"2023-04-21","cited_by_count":23},{"id":"2110.05722","title":"LightSeq2: Accelerated Training for Transformer-based Models on GPUs","created":"2021-10-12","cited_by_count":19},{"id":"2304.01926","title":"High-Throughput Vector Similarity Search in Knowledge Graphs","created":"2023-04-04","cited_by_count":19},{"id":"2206.14286","title":"TPU-KNN: K Nearest Neighbor Search at Peak FLOP/s","created":"2022-06-28","cited_by_count":18},{"id":"2209.06979","title":"Efficient Quantized Sparse Matrix Operations on Tensor Cores","created":"2022-09-14","cited_by_count":16},{"id":"2201.01863","title":"CFU Playground: Full-Stack Open-Source Framework for Tiny Machine Learning (tinyML) Acceleration on FPGAs","created":"2022-01-05","cited_by_count":11},{"id":"2010.02079","title":"NATSA: A Near-Data Processing Accelerator for Time Series Analysis","created":"2020-10-05","cited_by_count":10},{"id":"1702.05911","title":"Efficient Large-scale Approximate Nearest Neighbor Search on the GPU","created":"2017-02-20","cited_by_count":8},{"id":"2306.11182","title":"Co-design Hardware and Algorithm for Vector Search","created":"2023-06-19","cited_by_count":6},{"id":"1908.02640","title":"Near-Memory Computing: Past, Present, and Future","created":"2019-08-07","cited_by_count":5},{"id":"2005.04324","title":"Benchmarking High Bandwidth Memory on FPGAs","created":"2020-05-09","cited_by_count":5},{"id":"2102.09713","title":"A Compiler Infrastructure for Accelerator Generators","created":"2021-02-19","cited_by_count":5},{"id":"2109.06355","title":"Optimizing FPGA-based Accelerator Design for Large-Scale Molecular Similarity Search","created":"2021-09-13","cited_by_count":5},{"id":"2212.00939","title":"DisaggRec: Architecting Disaggregated Systems for Large-Scale Personalized Recommendation","created":"2022-12-02","cited_by_count":5},{"id":"1901.00275","title":"Vector and Line Quantization for Billion-scale Similarity Search on GPUs","created":"2019-01-02","cited_by_count":3},{"id":"2106.07102","title":"Farview: Disaggregated Memory with Operator Off-loading for Database Engines","created":"2021-06-13","cited_by_count":3}],"next_cursor":null}