{"list":"other","total":53,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2205.01068","title":"OPT: Open Pre-trained Transformer Language Models","created":"2022-05-02","cited_by_count":3512},{"id":"2203.15556","title":"Training Compute-Optimal Large Language Models","created":"2022-03-29","cited_by_count":3019},{"id":"1909.08053","title":"Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism","created":"2019-09-17","cited_by_count":1868},{"id":"2006.16668","title":"GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding","created":"2020-06-30","cited_by_count":1631},{"id":"1910.02054","title":"ZeRO: Memory Optimizations Toward Training Trillion Parameter Models","created":"2019-10-04","cited_by_count":1301},{"id":"1708.05031","title":"Neural Collaborative Filtering","created":"2017-08-16","cited_by_count":1111},{"id":"2112.06905","title":"GLaM: Efficient Scaling of Language Models with Mixture-of-Experts","created":"2021-12-13","cited_by_count":897},{"id":"1606.07792","title":"Wide & Deep Learning for Recommender Systems","created":"2016-06-24","cited_by_count":747},{"id":"2304.11277","title":"PyTorch FSDP: Experiences on Scaling Fully Sharded Data Parallel","created":"2023-04-21","cited_by_count":660},{"id":"1704.04760","title":"In-Datacenter Performance Analysis of a Tensor Processing Unit","created":"2017-04-16","cited_by_count":618},{"id":"1706.06978","title":"Deep Interest Network for Click-Through Rate Prediction","created":"2017-06-21","cited_by_count":544},{"id":"2211.05102","title":"Efficiently Scaling Transformer Inference","created":"2022-11-09","cited_by_count":539},{"id":"1708.05123","title":"Deep & Cross Network for Ad Click Predictions","created":"2017-08-17","cited_by_count":393},{"id":"1809.03672","title":"Deep Interest Evolution Network for Click-Through Rate Prediction","created":"2018-09-11","cited_by_count":338},{"id":"1906.00091","title":"Deep Learning Recommendation Model for Personalization and Recommendation Systems","created":"2019-05-31","cited_by_count":327},{"id":"2008.13535","title":"DCN V2: Improved Deep & Cross Network and Practical Lessons for Web-scale Learning to Rank Systems","created":"2020-08-19","cited_by_count":327},{"id":"2111.00364","title":"Sustainable AI: Environmental Implications, Challenges and Opportunities","created":"2021-10-30","cited_by_count":242},{"id":"2304.01433","title":"TPU v4: An Optically Reconfigurable Supercomputer for Machine Learning with Hardware Support for Embeddings","created":"2023-04-04","cited_by_count":202},{"id":"2204.05149","title":"The Carbon Footprint of Machine Learning Training Will Plateau, Then Shrink","created":"2022-04-11","cited_by_count":184},{"id":"1807.05358","title":"Beyond Data and Model Parallelism for Deep Neural Networks","created":"2018-07-14","cited_by_count":179},{"id":"2112.10684","title":"Efficient Large Scale Language Modeling with Mixtures of Experts","created":"2021-12-20","cited_by_count":175},{"id":"1905.06874","title":"Behavior Sequence Transformer for E-commerce Recommendation in Alibaba","created":"2019-05-15","cited_by_count":130},{"id":"2105.04663","title":"GSPMD: General and Scalable Parallelization for ML Computation Graphs","created":"2021-05-10","cited_by_count":111},{"id":"2301.04655","title":"ChatGPT is not all you need. A State of the Art Review of large Generative AI models","created":"2023-01-11","cited_by_count":86},{"id":"1906.03109","title":"The Architectural Implications of Facebook's DNN-based Personalized Recommendation","created":"2019-06-06","cited_by_count":83},{"id":"1901.05758","title":"Analysis of Large-Scale Multi-Tenant GPU Clusters for DNN Training Workloads","created":"2019-01-17","cited_by_count":79},{"id":"2104.05158","title":"Software-Hardware Co-design for Fast and Scalable Training of Deep Learning Recommendation Models","created":"2021-04-12","cited_by_count":78},{"id":"2011.02839","title":"Chasing Carbon: The Elusive Environmental Footprint of Computing","created":"2020-10-28","cited_by_count":72},{"id":"1706.03292","title":"Poseidon: An Efficient Communication Architecture for Distributed Deep Learning on GPU Clusters","created":"2017-06-11","cited_by_count":57},{"id":"2001.02772","title":"DeepRecSys: A System for Optimizing End-To-End At-scale Neural Recommendation Inference","created":"2020-01-08","cited_by_count":54},{"id":"1912.12953","title":"RecNMP: Accelerating Personalized Recommendation with Near-Memory Processing","created":"2019-12-30","cited_by_count":49},{"id":"2303.14006","title":"ASTRA-sim2.0: Modeling Hierarchical Networks and Disaggregated Systems for Large-model Training at Scale","created":"2023-03-24","cited_by_count":47},{"id":"1908.03072","title":"TensorDIMM: A Practical Near-Memory Processing Architecture for Embeddings and Tensor Operations in Deep Learning","created":"2019-08-08","cited_by_count":43},{"id":"2011.05497","title":"Understanding Training Efficiency of Deep Learning Recommendation Models at Scale","created":"2020-11-11","cited_by_count":43},{"id":"2102.00075","title":"RecSSD: Near Data Processing for Solid State Drive Based Recommendation Inference","created":"2021-01-29","cited_by_count":35},{"id":"2209.05310","title":"On the Factory Floor: ML Engineering for Industrial-Scale Ads Recommendation Models","created":"2022-09-12","cited_by_count":34},{"id":"2202.00433","title":"TopoOpt: Co-optimizing Network Topology and Parallelization Strategy for Distributed Training Jobs","created":"2022-02-01","cited_by_count":30},{"id":"2201.10095","title":"RecShard: Statistical Feature-Based Memory Optimization for Industry-Scale Neural Recommendation","created":"2022-01-25","cited_by_count":28},{"id":"2306.02781","title":"An Automated Survey of Generative Artificial Intelligence: Large Language Models, Architectures, Protocols, and Applications","created":"2023-06-05","cited_by_count":20},{"id":"2110.04478","title":"Themis: A Network Bandwidth-Aware Collective Scheduling Policy for Distributed Training of DL Models","created":"2021-10-09","cited_by_count":16},{"id":"2305.14516","title":"Chakra: Advancing Performance Benchmarking and Co-design using Standardized Execution Traces","created":"2023-05-23","cited_by_count":13},{"id":"2203.11014","title":"DHEN: A Deep and Hierarchical Ensemble Network for Large-Scale Click-Through Rate Prediction","created":"2022-03-11","cited_by_count":12},{"id":"2010.05037","title":"Cross-Stack Workload Characterization of Deep Recommendation Systems","created":"2020-10-10","cited_by_count":11},{"id":"2302.10872","title":"MP-Rec: Hardware-Software Co-Design to Enable Multi-Path Recommendation","created":"2023-02-21","cited_by_count":9},{"id":"2302.02825","title":"Computation vs. Communication Scaling for Future Transformers on Future Hardware","created":"2023-02-06","cited_by_count":7},{"id":"2211.03309","title":"DeepFlow: A Cross-Stack Pathfinding Framework for Distributed AI Systems","created":"2022-11-07","cited_by_count":6},{"id":"2301.04122","title":"Mystique: Enabling Accurate and Scalable Generation of Production AI Benchmarks","created":"2022-12-16","cited_by_count":5},{"id":"2211.16648","title":"COMET: A Comprehensive Cluster Design Methodology for Distributed Deep Learning Training","created":"2022-11-30","cited_by_count":2}],"next_cursor":null}