{"list":"other","total":105,"rows":[{"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":"2004.04906","title":"Dense Passage Retrieval for Open-Domain Question Answering","created":"2020-04-10","cited_by_count":3824},{"id":"2108.07732","title":"Program Synthesis with Large Language Models","created":"2021-08-16","cited_by_count":3637},{"id":"2308.12950","title":"Code Llama: Open Foundation Models for Code","created":"2023-08-24","cited_by_count":2139},{"id":"2308.14508","title":"LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding","created":"2023-08-28","cited_by_count":1417},{"id":"2409.12186","title":"Qwen2.5-Coder Technical Report","created":"2024-09-18","cited_by_count":1203},{"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":"2302.00093","title":"Large Language Models Can Be Easily Distracted by Irrelevant Context","created":"2023-01-31","cited_by_count":841},{"id":"2305.06161","title":"StarCoder: may the source be with you!","created":"2023-05-09","cited_by_count":799},{"id":"2402.19173","title":"StarCoder 2 and The Stack v2: The Next Generation","created":"2024-02-29","cited_by_count":502},{"id":"2501.05366","title":"Search-o1: Agentic Search-Enhanced Large Reasoning Models","created":"2025-01-09","cited_by_count":433},{"id":"2406.02069","title":"PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling","created":"2024-06-04","cited_by_count":432},{"id":"2310.01558","title":"Making Retrieval-Augmented Language Models Robust to Irrelevant Context","created":"2023-10-02","cited_by_count":369},{"id":"2303.12570","title":"RepoCoder: Repository-Level Code Completion Through Iterative Retrieval and Generation","created":"2023-03-22","cited_by_count":367},{"id":"2203.03850","title":"UniXcoder: Unified Cross-Modal Pre-training for Code Representation","created":"2022-03-08","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":"2401.07339","title":"CodeAgent: Enhancing Code Generation with Tool-Integrated Agent Systems for Real-World Repo-level Coding Challenges","created":"2024-01-14","cited_by_count":282},{"id":"2311.04934","title":"Prompt Cache: Modular Attention Reuse for Low-Latency Inference","created":"2023-11-07","cited_by_count":268},{"id":"2312.02120","title":"Magicoder: Empowering Code Generation with OSS-Instruct","created":"2023-12-04","cited_by_count":256},{"id":"2407.11550","title":"Ada-KV: Optimizing KV Cache Eviction by Adaptive Budget Allocation for Efficient LLM Inference","created":"2024-07-16","cited_by_count":235},{"id":"2310.11248","title":"CrossCodeEval: A Diverse and Multilingual Benchmark for Cross-File Code Completion","created":"2023-10-17","cited_by_count":183},{"id":"2207.05987","title":"DocPrompting: Generating Code by Retrieving the Docs","created":"2022-07-13","cited_by_count":153},{"id":"2403.03163","title":"Design2Code: Benchmarking Multimodal Code Generation for Automated Front-End Engineering","created":"2024-03-05","cited_by_count":152},{"id":"2108.11601","title":"Retrieval Augmented Code Generation and Summarization","created":"2021-08-26","cited_by_count":149},{"id":"2303.07678","title":"Query2doc: Query Expansion with Large Language Models","created":"2023-03-14","cited_by_count":149},{"id":"2309.12499","title":"CodePlan: Repository-level Coding using LLMs and Planning","created":"2023-09-21","cited_by_count":140},{"id":"2212.09420","title":"Large Language Models Meet NL2Code: A Survey","created":"2022-12-19","cited_by_count":138},{"id":"2403.17927","title":"MAGIS: LLM-Based Multi-Agent Framework for GitHub Issue Resolution","created":"2024-03-26","cited_by_count":134},{"id":"2203.07722","title":"ReACC: A Retrieval-Augmented Code Completion Framework","created":"2022-03-15","cited_by_count":119},{"id":"2501.01257","title":"CodeElo: Benchmarking Competition-level Code Generation of LLMs with Human-comparable Elo Ratings","created":"2025-01-02","cited_by_count":115},{"id":"2306.14893","title":"LongCoder: A Long-Range Pre-trained Language Model for Code Completion","created":"2023-06-26","cited_by_count":112},{"id":"2502.14382","title":"S*: Test Time Scaling for Code Generation","created":"2025-02-20","cited_by_count":98},{"id":"2409.20550","title":"LLM Hallucinations in Practical Code Generation: Phenomena, Mechanism, and Mitigation","created":"2024-09-30","cited_by_count":93},{"id":"2501.05040","title":"SWE-Fixer: Training Open-Source LLMs for Effective and Efficient GitHub Issue Resolution","created":"2025-01-09","cited_by_count":90},{"id":"2405.14918","title":"AnalogCoder: Analog Circuit Design via Training-Free Code Generation","created":"2024-05-23","cited_by_count":84},{"id":"2403.07865","title":"CodeAttack: Revealing Safety Generalization Challenges of Large Language Models via Code Completion","created":"2024-03-12","cited_by_count":76},{"id":"2402.12065","title":"WKVQuant: Quantizing Weight and Key/Value Cache for Large Language Models Gains More","created":"2024-02-19","cited_by_count":69},{"id":"2308.11396","title":"Towards an Understanding of Large Language Models in Software Engineering Tasks","created":"2023-08-22","cited_by_count":68},{"id":"2311.10372","title":"A Survey of Large Language Models for Code: Evolution, Benchmarking, and Future Trends","created":"2023-11-17","cited_by_count":66},{"id":"2212.10007","title":"CoCoMIC: Code Completion By Jointly Modeling In-file and Cross-file Context","created":"2022-12-20","cited_by_count":65},{"id":"2507.23361","title":"SWE-Exp: Experience-Driven Software Issue Resolution","created":"2025-07-31","cited_by_count":65},{"id":"2311.07989","title":"Unifying the Perspectives of NLP and Software Engineering: A Survey on Language Models for Code","created":"2023-11-14","cited_by_count":62},{"id":"2409.09030","title":"Agents in Software Engineering: Survey, Landscape, and Vision","created":"2024-09-13","cited_by_count":60},{"id":"2406.01422","title":"Alibaba LingmaAgent: Improving Automated Issue Resolution via Comprehensive Repository Exploration","created":"2024-06-03","cited_by_count":58},{"id":"2310.04951","title":"CodeTransOcean: A Comprehensive Multilingual Benchmark for Code Translation","created":"2023-10-08","cited_by_count":57},{"id":"2403.10059","title":"Repoformer: Selective Retrieval for Repository-Level Code Completion","created":"2024-03-15","cited_by_count":55},{"id":"2003.07914","title":"Big Code != Big Vocabulary: Open-Vocabulary Models for Source Code","created":"2020-03-17","cited_by_count":54},{"id":"2507.23348","title":"SWE-Debate: Competitive Multi-Agent Debate for Software Issue Resolution","created":"2025-07-31","cited_by_count":53},{"id":"2107.07112","title":"On the Evaluation of Neural Code Summarization","created":"2021-07-15","cited_by_count":48},{"id":"2407.19487","title":"RLCoder: Reinforcement Learning for Repository-Level Code Completion","created":"2024-07-28","cited_by_count":44},{"id":"2306.10998","title":"RepoFusion: Training Code Models to Understand Your Repository","created":"2023-06-19","cited_by_count":40},{"id":"2405.19782","title":"Dataflow-Guided Retrieval Augmentation for Repository-Level Code Completion","created":"2024-05-30","cited_by_count":40},{"id":"2406.07003","title":"GraphCoder: Enhancing Repository-Level Code Completion via Code Context Graph-based Retrieval and Language Model","created":"2024-06-11","cited_by_count":40},{"id":"2402.16197","title":"Language Models for Code Completion: A Practical Evaluation","created":"2024-02-25","cited_by_count":39},{"id":"2104.05740","title":"A Replication Study of Dense Passage Retriever","created":"2021-04-12","cited_by_count":37},{"id":"2108.12987","title":"CAST: Enhancing Code Summarization with Hierarchical Splitting and Reconstruction of Abstract Syntax Trees","created":"2021-08-30","cited_by_count":32},{"id":"2402.14323","title":"REPOFUSE: Repository-Level Code Completion with Fused Dual Context","created":"2024-02-22","cited_by_count":32},{"id":"2103.09499","title":"Code Completion by Modeling Flattened Abstract Syntax Trees as Graphs","created":"2021-03-17","cited_by_count":30},{"id":"2401.06391","title":"Teaching Code LLMs to Use Autocompletion Tools in Repository-Level Code Generation","created":"2024-01-12","cited_by_count":30},{"id":"2406.06918","title":"HumanEvo: An Evolution-aware Benchmark for More Realistic Evaluation of Repository-level Code Generation","created":"2024-06-11","cited_by_count":28},{"id":"2409.15154","title":"RMCBench: Benchmarking Large Language Models' Resistance to Malicious Code","created":"2024-09-23","cited_by_count":28},{"id":"2203.02700","title":"RACE: Retrieval-Augmented Commit Message Generation","created":"2022-03-05","cited_by_count":27},{"id":"2303.17780","title":"AceCoder: Utilizing Existing Code to Enhance Code Generation","created":"2023-03-31","cited_by_count":25},{"id":"2505.04606","title":"OmniGIRL: A Multilingual and Multimodal Benchmark for GitHub Issue Resolution","created":"2025-05-07","cited_by_count":24},{"id":"2107.01933","title":"CoCoSum: Contextual Code Summarization with Multi-Relational Graph Neural Network","created":"2021-07-05","cited_by_count":22},{"id":"2204.03293","title":"CoCoSoDa: Effective Contrastive Learning for Code Search","created":"2022-04-07","cited_by_count":22},{"id":"2503.20589","title":"What to Retrieve for Effective Retrieval-Augmented Code Generation? An Empirical Study and Beyond","created":"2025-03-26","cited_by_count":22},{"id":"2406.10018","title":"STALL+: Boosting LLM-based Repository-level Code Completion with Static Analysis","created":"2024-06-14","cited_by_count":21},{"id":"2407.20042","title":"When to Stop? Towards Efficient Code Generation in LLMs with Excess Token Prevention","created":"2024-07-29","cited_by_count":21},{"id":"2408.13204","title":"DOMAINEVAL: An Auto-Constructed Benchmark for Multi-Domain Code Generation","created":"2024-08-23","cited_by_count":21},{"id":"2502.18297","title":"DeepCircuitX: A Comprehensive Repository-Level Dataset for RTL Code Understanding, Generation, and PPA Analysis","created":"2025-02-25","cited_by_count":21},{"id":"2107.05373","title":"On the Evaluation of Commit Message Generation Models: An Experimental Study","created":"2021-07-12","cited_by_count":20},{"id":"2308.09313","title":"Domain Adaptive Code Completion via Language Models and Decoupled Domain Databases","created":"2023-08-18","cited_by_count":19},{"id":"2410.09812","title":"Unraveling the Potential of Large Language Models in Code Translation: How Far Are We?","created":"2024-10-13","cited_by_count":17},{"id":"2407.00456","title":"Beyond Functional Correctness: Investigating Coding Style Inconsistencies in Large Language Models","created":"2024-06-29","cited_by_count":15},{"id":"2310.08069","title":"Rethinking Negative Pairs in Code Search","created":"2023-10-12","cited_by_count":14},{"id":"2409.06679","title":"E2LLM: Encoder Elongated Large Language Models for Long-Context Understanding and Reasoning","created":"2024-09-10","cited_by_count":13},{"id":"2412.18573","title":"Top General Performance = Top Domain Performance? DomainCodeBench: A Multi-domain Code Generation Benchmark","created":"2024-12-24","cited_by_count":13},{"id":"1611.08307","title":"Learning Python Code Suggestion with a Sparse Pointer Network","created":"2016-11-24","cited_by_count":12},{"id":"2310.01446","title":"Adaptive-Solver Framework for Dynamic Strategy Selection in Large Language Model Reasoning","created":"2023-10-01","cited_by_count":12},{"id":"2401.14727","title":"SparseCoder: Identifier-Aware Sparse Transformer for File-Level Code Summarization","created":"2024-01-26","cited_by_count":11},{"id":"2406.11589","title":"CoSQA+: Pioneering the Multi-Choice Code Search Benchmark with Test-Driven Agents","created":"2024-06-17","cited_by_count":11},{"id":"2408.05542","title":"You Augment Me: Exploring ChatGPT-based Data Augmentation for Semantic Code Search","created":"2024-08-10","cited_by_count":11},{"id":"2203.15287","title":"Accelerating Code Search with Deep Hashing and Code Classification","created":"2022-03-29","cited_by_count":10},{"id":"2401.05926","title":"Using Large Language Models for Commit Message Generation: A Preliminary Study","created":"2024-01-11","cited_by_count":10},{"id":"2401.08376","title":"KADEL: Knowledge-Aware Denoising Learning for Commit Message Generation","created":"2024-01-16","cited_by_count":10},{"id":"2404.14824","title":"Automated Commit Message Generation with Large Language Models: An Empirical Study and Beyond","created":"2024-04-23","cited_by_count":10},{"id":"2409.15204","title":"RAMBO: Enhancing RAG-based Repository-Level Method Body Completion","created":"2024-09-23","cited_by_count":10},{"id":"2504.08734","title":"Towards an Understanding of Context Utilization in Code Intelligence","created":"2025-04-11","cited_by_count":10},{"id":"2208.11271","title":"Tackling Long Code Search with Splitting, Encoding, and Aggregating","created":"2022-08-24","cited_by_count":9},{"id":"2308.10759","title":"EALink: An Efficient and Accurate Pre-trained Framework for Issue-Commit Link Recovery","created":"2023-08-21","cited_by_count":9},{"id":"2208.11274","title":"Revisiting Code Search in a Two-Stage Paradigm","created":"2022-08-24","cited_by_count":8},{"id":"2308.13416","title":"SoTaNa: The Open-Source Software Development Assistant","created":"2023-08-25","cited_by_count":8},{"id":"2407.13271","title":"Identifying Smart Contract Security Issues in Code Snippets from Stack Overflow","created":"2024-07-18","cited_by_count":8},{"id":"2105.09630","title":"Enriching Query Semantics for Code Search with Reinforcement Learning","created":"2021-05-20","cited_by_count":7},{"id":"2408.06037","title":"Hyperion: Unveiling DApp Inconsistencies using LLM and Dataflow-Guided Symbolic Execution","created":"2024-08-12","cited_by_count":7},{"id":"2410.22240","title":"Are Decoder-Only Large Language Models the Silver Bullet for Code Search?","created":"2024-10-29","cited_by_count":7},{"id":"2409.13122","title":"RepoGenReflex: Enhancing Repository-Level Code Completion with Verbal Reinforcement and Retrieval-Augmented Generation","created":"2024-09-19","cited_by_count":6},{"id":"2504.19444","title":"Large Language Models are Qualified Benchmark Builders: Rebuilding Pre-Training Datasets for Advancing Code Intelligence Tasks","created":"2025-04-28","cited_by_count":6}],"next_cursor":"100"}