{"list":"other","total":121,"rows":[{"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":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"2309.06180","title":"Efficient Memory Management for Large Language Model Serving with PagedAttention","created":"2023-09-12","cited_by_count":5944},{"id":"2203.15556","title":"Training Compute-Optimal Large Language Models","created":"2022-03-29","cited_by_count":3019},{"id":"2307.08691","title":"FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning","created":"2023-07-17","cited_by_count":2598},{"id":"2308.12950","title":"Code Llama: Open Foundation Models for Code","created":"2023-08-24","cited_by_count":2139},{"id":"1909.08053","title":"Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism","created":"2019-09-17","cited_by_count":1868},{"id":"2203.07814","title":"Competition-Level Code Generation with AlphaCode","created":"2022-02-08","cited_by_count":1462},{"id":"1910.02054","title":"ZeRO: Memory Optimizations Toward Training Trillion Parameter Models","created":"2019-10-04","cited_by_count":1301},{"id":"2401.14196","title":"DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence","created":"2024-01-25","cited_by_count":1181},{"id":"2406.17557","title":"The FineWeb Datasets: Decanting the Web for the Finest Text Data at Scale","created":"2024-06-25","cited_by_count":1160},{"id":"2405.04434","title":"DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model","created":"2024-05-07","cited_by_count":1135},{"id":"2109.00859","title":"CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation","created":"2021-09-02","cited_by_count":906},{"id":"2102.04664","title":"CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation","created":"2021-02-09","cited_by_count":744},{"id":"2306.08568","title":"WizardCoder: Empowering Code Large Language Models with Evol-Instruct","created":"2023-06-14","cited_by_count":733},{"id":"2107.06499","title":"Deduplicating Training Data Makes Language Models Better","created":"2021-07-14","cited_by_count":714},{"id":"2401.02954","title":"DeepSeek LLM: Scaling Open-Source Language Models with Longtermism","created":"2024-01-05","cited_by_count":642},{"id":"2009.08366","title":"GraphCodeBERT: Pre-training Code Representations with Data Flow","created":"2020-09-17","cited_by_count":609},{"id":"2306.11644","title":"Textbooks Are All You Need","created":"2023-06-20","cited_by_count":569},{"id":"2406.15877","title":"BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions","created":"2024-06-22","cited_by_count":546},{"id":"2407.08608","title":"FlashAttention-3: Fast and Accurate Attention with Asynchrony and Low-precision","created":"2024-07-11","cited_by_count":519},{"id":"2402.19173","title":"StarCoder 2 and The Stack v2: The Next Generation","created":"2024-02-29","cited_by_count":502},{"id":"2204.05999","title":"InCoder: A Generative Model for Code Infilling and Synthesis","created":"2022-04-12","cited_by_count":498},{"id":"2305.16264","title":"Scaling Data-Constrained Language Models","created":"2023-05-25","cited_by_count":403},{"id":"2207.10397","title":"CodeT: Code Generation with Generated Tests","created":"2022-07-21","cited_by_count":384},{"id":"2203.03850","title":"UniXcoder: Unified Cross-Modal Pre-training for Code Representation","created":"2022-03-08","cited_by_count":361},{"id":"2211.15533","title":"The Stack: 3 TB of permissively licensed source code","created":"2022-11-20","cited_by_count":359},{"id":"2207.01780","title":"CodeRL: Mastering Code Generation through Pretrained Models and Deep Reinforcement Learning","created":"2022-07-05","cited_by_count":358},{"id":"1909.03496","title":"Devign: Effective Vulnerability Identification by Learning Comprehensive Program Semantics via Graph Neural Networks","created":"2019-09-08","cited_by_count":272},{"id":"2102.01293","title":"Scaling Laws for Transfer","created":"2021-02-02","cited_by_count":272},{"id":"2006.03511","title":"Unsupervised Translation of Programming Languages","created":"2020-06-05","cited_by_count":263},{"id":"2312.02120","title":"Magicoder: Empowering Code Generation with OSS-Instruct","created":"2023-12-04","cited_by_count":256},{"id":"2207.14255","title":"Efficient Training of Language Models to Fill in the Middle","created":"2022-07-28","cited_by_count":255},{"id":"2402.14658","title":"OpenCodeInterpreter: Integrating Code Generation with Execution and Refinement","created":"2024-02-22","cited_by_count":247},{"id":"2401.16380","title":"Rephrasing the Web: A Recipe for Compute and Data-Efficient Language Modeling","created":"2024-01-29","cited_by_count":161},{"id":"2401.00448","title":"Beyond Chinchilla-Optimal: Accounting for Inference in Language Model Scaling Laws","created":"2023-12-31","cited_by_count":159},{"id":"2309.14717","title":"QA-LoRA: Quantization-Aware Low-Rank Adaptation of Large Language Models","created":"2023-09-26","cited_by_count":155},{"id":"2406.11409","title":"CodeGemma: Open Code Models Based on Gemma","created":"2024-06-17","cited_by_count":150},{"id":"2201.06642","title":"Towards a Cleaner Document-Oriented Multilingual Crawled Corpus","created":"2022-01-17","cited_by_count":143},{"id":"2305.06599","title":"Structured Chain-of-Thought Prompting for Code Generation","created":"2023-05-11","cited_by_count":138},{"id":"1812.06469","title":"The Adverse Effects of Code Duplication in Machine Learning Models of Code","created":"2018-12-16","cited_by_count":126},{"id":"2405.04324","title":"Granite Code Models: A Family of Open Foundation Models for Code Intelligence","created":"2024-05-07","cited_by_count":117},{"id":"1909.03341","title":"Neural Machine Translation with Byte-Level Subwords","created":"2019-09-07","cited_by_count":115},{"id":"2307.04349","title":"RLTF: Reinforcement Learning from Unit Test Feedback","created":"2023-07-10","cited_by_count":114},{"id":"2403.08540","title":"Language models scale reliably with over-training and on downstream tasks","created":"2024-03-13","cited_by_count":113},{"id":"2212.10264","title":"ReCode: Robustness Evaluation of Code Generation Models","created":"2022-12-20","cited_by_count":103},{"id":"2301.13816","title":"Execution-based Code Generation using Deep Reinforcement Learning","created":"2023-01-31","cited_by_count":99},{"id":"2206.06888","title":"CERT: Continual Pre-Training on Sketches for Library-Oriented Code Generation","created":"2022-06-14","cited_by_count":87},{"id":"2409.03733","title":"Planning In Natural Language Improves LLM Search For Code Generation","created":"2024-09-05","cited_by_count":83},{"id":"2007.04973","title":"Contrastive Code Representation Learning","created":"2020-07-09","cited_by_count":76},{"id":"2003.13848","title":"Code Prediction by Feeding Trees to Transformers","created":"2020-03-30","cited_by_count":70},{"id":"2102.07492","title":"DOBF: A Deobfuscation Pre-Training Objective for Programming Languages","created":"2021-02-15","cited_by_count":68},{"id":"2108.04556","title":"SynCoBERT: Syntax-Guided Multi-Modal Contrastive Pre-Training for Code Representation","created":"2021-08-10","cited_by_count":63},{"id":"1910.05923","title":"Code Generation as a Dual Task of Code Summarization","created":"2019-10-14","cited_by_count":62},{"id":"1805.08490","title":"Generative Code Modeling with Graphs","created":"2018-05-22","cited_by_count":60},{"id":"1806.07336","title":"Neural Code Comprehension: A Learnable Representation of Code Semantics","created":"2018-06-19","cited_by_count":59},{"id":"2206.08474","title":"XLCoST: A Benchmark Dataset for Cross-lingual Code Intelligence","created":"2022-06-16","cited_by_count":56},{"id":"2206.07585","title":"NatGen: Generative pre-training by \"Naturalizing\" source code","created":"2022-06-15","cited_by_count":54},{"id":"2311.11077","title":"Adapters: A Unified Library for Parameter-Efficient and Modular Transfer Learning","created":"2023-11-18","cited_by_count":53},{"id":"2009.02731","title":"Self-Supervised Contrastive Learning for Code Retrieval and Summarization via Semantic-Preserving Transformations","created":"2020-09-06","cited_by_count":49},{"id":"2008.01566","title":"On the Generalizability of Neural Program Models with respect to Semantic-Preserving Program Transformations","created":"2020-07-31","cited_by_count":44},{"id":"2207.03578","title":"Code Translation with Compiler Representations","created":"2022-06-30","cited_by_count":42},{"id":"1909.09029","title":"DIRE: A Neural Approach to Decompiled Identifier Naming","created":"2019-09-19","cited_by_count":36},{"id":"1506.01159","title":"On the \"Naturalness\" of Buggy Code","created":"2015-06-03","cited_by_count":35},{"id":"2206.05239","title":"StructCoder: Structure-Aware Transformer for Code Generation","created":"2022-06-10","cited_by_count":34},{"id":"2305.05383","title":"Code Execution with Pre-trained Language Models","created":"2023-05-08","cited_by_count":34},{"id":"2401.03003","title":"AST-T5: Structure-Aware Pretraining for Code Generation and Understanding","created":"2024-01-05","cited_by_count":33},{"id":"1803.09544","title":"A General Path-Based Representation for Predicting Program Properties","created":"2018-03-26","cited_by_count":29},{"id":"2112.02268","title":"Bridging Pre-trained Models and Downstream Tasks for Source Code Understanding","created":"2021-12-04","cited_by_count":28},{"id":"2306.07487","title":"TRACED: Execution-aware Pre-training for Source Code","created":"2023-06-13","cited_by_count":27},{"id":"2311.14904","title":"LLM-Assisted Code Cleaning For Training Accurate Code Generators","created":"2023-11-25","cited_by_count":27},{"id":"2407.14044","title":"ECCO: Can We Improve Model-Generated Code Efficiency Without Sacrificing Functional Correctness?","created":"2024-07-19","cited_by_count":27},{"id":"2202.08975","title":"Probing Pretrained Models of Source Code","created":"2022-02-16","cited_by_count":26},{"id":"2106.10158","title":"Learning to Complete Code with Sketches","created":"2021-06-18","cited_by_count":23},{"id":"2403.03894","title":"IRCoder: Intermediate Representations Make Language Models Robust Multilingual Code Generators","created":"2024-03-06","cited_by_count":23},{"id":"2311.07811","title":"In-context Learning Generalizes, But Not Always Robustly: The Case of Syntax","created":"2023-11-13","cited_by_count":22},{"id":"2305.12050","title":"AI-assisted Code Authoring at Scale: Fine-tuning, deploying, and mixed methods evaluation","created":"2023-05-20","cited_by_count":21},{"id":"2106.08704","title":"Memorization and Generalization in Neural Code Intelligence Models","created":"2021-06-16","cited_by_count":19},{"id":"2405.07518","title":"SambaNova SN40L: Scaling the AI Memory Wall with Dataflow and Composition of Experts","created":"2024-05-13","cited_by_count":18},{"id":"2406.16441","title":"UniCoder: Scaling Code Large Language Model via Universal Code","created":"2024-06-24","cited_by_count":18},{"id":"2105.09352","title":"DeepDebug: Fixing Python Bugs Using Stack Traces, Backtranslation, and Code Skeletons","created":"2021-05-19","cited_by_count":17},{"id":"2007.13239","title":"funcGNN: A Graph Neural Network Approach to Program Similarity","created":"2020-07-26","cited_by_count":16},{"id":"2308.07655","title":"From Commit Message Generation to History-Aware Commit Message Completion","created":"2023-08-15","cited_by_count":16},{"id":"2111.02671","title":"GraphSearchNet: Enhancing GNNs via Capturing Global Dependencies for Semantic Code Search","created":"2021-11-04","cited_by_count":15},{"id":"2012.04188","title":"Learning to Represent Programs with Heterogeneous Graphs","created":"2020-12-08","cited_by_count":14},{"id":"2405.17057","title":"ReflectionCoder: Learning from Reflection Sequence for Enhanced One-off Code Generation","created":"2024-05-27","cited_by_count":14},{"id":"2402.04141","title":"Multi-line AI-assisted Code Authoring","created":"2024-02-06","cited_by_count":13},{"id":"2205.11116","title":"Summarize and Generate to Back-translate: Unsupervised Translation of Programming Languages","created":"2022-05-23","cited_by_count":12},{"id":"1809.05193","title":"Context2Name: A Deep Learning-Based Approach to Infer Natural Variable Names from Usage Contexts","created":"2018-08-31","cited_by_count":11},{"id":"2204.09191","title":"Unleashing the Power of Compiler Intermediate Representation to Enhance Neural Program Embeddings","created":"2022-04-20","cited_by_count":10},{"id":"2211.04673","title":"Syntax-Aware On-the-Fly Code Completion","created":"2022-11-09","cited_by_count":10},{"id":"2308.03312","title":"Exploiting Code Symmetries for Learning Program Semantics","created":"2023-08-07","cited_by_count":10},{"id":"2204.03498","title":"On the Effectiveness of Pretrained Models for API Learning","created":"2022-04-05","cited_by_count":9},{"id":"2212.10017","title":"Unveiling Code Pre-Trained Models: Investigating Syntax and Semantics Capacities","created":"2022-12-20","cited_by_count":9},{"id":"2308.03873","title":"Evaluating and Explaining Large Language Models for Code Using Syntactic Structures","created":"2023-08-07","cited_by_count":9},{"id":"2408.04820","title":"Natural Language Outlines for Code: Literate Programming in the LLM Era","created":"2024-08-09","cited_by_count":9},{"id":"2104.14671","title":"SYNFIX: Automatically Fixing Syntax Errors using Compiler Diagnostics","created":"2021-04-29","cited_by_count":8},{"id":"2206.11147","title":"reStructured Pre-training","created":"2022-06-22","cited_by_count":8},{"id":"2308.12773","title":"Pre-training Code Representation with Semantic Flow Graph for Effective Bug Localization","created":"2023-08-24","cited_by_count":8}],"next_cursor":"100"}