{"list":"other","total":54,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"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":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"2309.06180","title":"Efficient Memory Management for Large Language Model Serving with PagedAttention","created":"2023-09-12","cited_by_count":5944},{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"id":"2102.05918","title":"Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision","created":"2021-02-11","cited_by_count":3864},{"id":"1910.03771","title":"HuggingFace's Transformers: State-of-the-art Natural Language Processing","created":"2019-10-09","cited_by_count":2218},{"id":"2308.12950","title":"Code Llama: Open Foundation Models for Code","created":"2023-08-24","cited_by_count":2139},{"id":"2211.05100","title":"BLOOM: A 176B-Parameter Open-Access Multilingual Language Model","created":"2022-11-09","cited_by_count":1984},{"id":"1909.08053","title":"Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism","created":"2019-09-17","cited_by_count":1868},{"id":"2107.07651","title":"Align before Fuse: Vision and Language Representation Learning with Momentum Distillation","created":"2021-07-16","cited_by_count":1619},{"id":"2002.08155","title":"CodeBERT: A Pre-Trained Model for Programming and Natural Languages","created":"2020-02-19","cited_by_count":1310},{"id":"1907.02189","title":"On the Convergence of FedAvg on Non-IID Data","created":"2019-07-04","cited_by_count":1229},{"id":"1901.07291","title":"Cross-lingual Language Model Pretraining","created":"2019-01-22","cited_by_count":1090},{"id":"2305.06161","title":"StarCoder: may the source be with you!","created":"2023-05-09","cited_by_count":799},{"id":"2009.08366","title":"GraphCodeBERT: Pre-training Code Representations with Data Flow","created":"2020-09-17","cited_by_count":609},{"id":"2003.01332","title":"Heterogeneous Graph Transformer","created":"2020-03-03","cited_by_count":582},{"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":"2206.06488","title":"Multimodal Learning with Transformers: A Survey","created":"2022-06-13","cited_by_count":400},{"id":"2107.00135","title":"Attention Bottlenecks for Multimodal Fusion","created":"2021-06-30","cited_by_count":361},{"id":"2305.07922","title":"CodeT5+: Open Code Large Language Models for Code Understanding and Generation","created":"2023-05-13","cited_by_count":333},{"id":"2307.10169","title":"Challenges and Applications of Large Language Models","created":"2023-07-19","cited_by_count":254},{"id":"2302.06527","title":"An Empirical Evaluation of Using Large Language Models for Automated Unit Test Generation","created":"2023-02-13","cited_by_count":194},{"id":"2206.11861","title":"Automatic Generation of Programming Exercises and Code Explanations using Large Language Models","created":"2022-06-03","cited_by_count":126},{"id":"2103.11943","title":"BERT: A Review of Applications in Natural Language Processing and Understanding","created":"2021-03-22","cited_by_count":109},{"id":"2211.02265","title":"Experiences from Using Code Explanations Generated by Large Language Models in a Web Software Development E-Book","created":"2022-11-04","cited_by_count":84},{"id":"2309.07062","title":"Large Language Models for Compiler Optimization","created":"2023-09-11","cited_by_count":52},{"id":"2304.13187","title":"AI-assisted coding: Experiments with GPT-4","created":"2023-04-25","cited_by_count":43},{"id":"2209.02235","title":"Automatic Code Documentation Generation Using GPT-3","created":"2022-09-06","cited_by_count":37},{"id":"2401.12554","title":"Can Large Language Models Write Parallel Code?","created":"2024-01-23","cited_by_count":36},{"id":"2309.07103","title":"Comparing Llama-2 and GPT-3 LLMs for HPC kernels generation","created":"2023-09-12","cited_by_count":30},{"id":"2306.15121","title":"Evaluation of OpenAI Codex for HPC Parallel Programming Models Kernel Generation","created":"2023-06-27","cited_by_count":22},{"id":"2311.12833","title":"HPC-GPT: Integrating Large Language Model for High-Performance Computing","created":"2023-10-03","cited_by_count":22},{"id":"2306.14979","title":"LM4HPC: Towards Effective Language Model Application in High-Performance Computing","created":"2023-06-26","cited_by_count":18},{"id":"2305.05779","title":"Learning to Parallelize with OpenMP by Augmented Heterogeneous AST Representation","created":"2023-05-09","cited_by_count":14},{"id":"2308.09440","title":"Scope is all you need: Transforming LLMs for HPC Code","created":"2023-08-18","cited_by_count":12},{"id":"2312.13322","title":"MonoCoder: Domain-Specific Code Language Model for HPC Codes and Tasks","created":"2023-12-20","cited_by_count":12},{"id":"2112.10878","title":"Enabling NAS with Automated Super-Network Generation","created":"2021-12-20","cited_by_count":11},{"id":"2306.17281","title":"HPC-Coder: Modeling Parallel Programs using Large Language Models","created":"2023-06-29","cited_by_count":11},{"id":"2308.07505","title":"Data Race Detection Using Large Language Models","created":"2023-08-15","cited_by_count":11},{"id":"2204.12835","title":"Learning to Parallelize in a Shared-Memory Environment with Transformers","created":"2022-04-27","cited_by_count":10},{"id":"2305.11999","title":"Advising OpenMP Parallelization via a Graph-Based Approach with Transformers","created":"2023-05-16","cited_by_count":10},{"id":"2203.00611","title":"Learning Intermediate Representations using Graph Neural Networks for NUMA and Prefetchers Optimization","created":"2022-03-01","cited_by_count":9},{"id":"2308.08002","title":"Quantifying OpenMP: Statistical Insights into Usage and Adoption","created":"2023-08-15","cited_by_count":9},{"id":"2310.00247","title":"Bridging the Gap Between Foundation Models and Heterogeneous Federated Learning","created":"2023-09-30","cited_by_count":9},{"id":"2005.13304","title":"ComPar: Optimized Multi-Compiler for Automatic OpenMP S2S Parallelization","created":"2020-05-27","cited_by_count":8},{"id":"2304.12568","title":"Performance Optimization using Multimodal Modeling and Heterogeneous GNN","created":"2023-04-25","cited_by_count":7},{"id":"2305.09438","title":"MPI-rical: Data-Driven MPI Distributed Parallelism Assistance with Transformers","created":"2023-05-16","cited_by_count":5},{"id":"2305.03843","title":"REINFOREST: Reinforcing Semantic Code Similarity for Cross-Lingual Code Search Models","created":"2023-05-05","cited_by_count":3},{"id":"2306.00210","title":"PERFOGRAPH: A Numerical Aware Program Graph Representation for Performance Optimization and Program Analysis","created":"2023-05-31","cited_by_count":3},{"id":"2311.06505","title":"CompCodeVet: A Compiler-guided Validation and Enhancement Approach for Code Dataset","created":"2023-11-11","cited_by_count":3}],"next_cursor":null}