{"total":98,"rows":[{"id":"2412.20367","title":"Enhancing Code LLMs with Reinforcement Learning in Code Generation: A Survey","created":"2024-12-29","cited_by_count":83,"area":null},{"id":"2501.09655","title":"A Survey of Research in Large Language Models for Electronic Design Automation","created":"2025-01-16","cited_by_count":41,"area":null},{"id":"2407.09007","title":"Benchmarking Language Model Creativity: A Case Study on Code Generation","created":"2024-07-12","cited_by_count":40,"area":null},{"id":"2502.06215","title":"LessLeak-Bench: A First Investigation of Data Leakage in LLMs Across 83 Software Engineering Benchmarks","created":"2025-02-10","cited_by_count":37,"area":null},{"id":"2411.12644","title":"CodeXEmbed: A Generalist Embedding Model Family for Multiligual and Multi-task Code Retrieval","created":"2024-11-19","cited_by_count":34,"area":null},{"id":"2410.15756","title":"Automated Proof Generation for Rust Code via Self-Evolution","created":"2024-10-21","cited_by_count":33,"area":null},{"id":"2505.06371","title":"The ML.ENERGY Benchmark: Toward Automated Inference Energy Measurement and Optimization","created":"2025-05-09","cited_by_count":33,"area":null},{"id":"2408.10718","title":"CodeJudge-Eval: Can Large Language Models be Good Judges in Code Understanding?","created":"2024-08-20","cited_by_count":30,"area":null},{"id":"2409.04556","title":"How Does Code Pretraining Affect Language Model Task Performance?","created":"2024-09-06","cited_by_count":28,"area":null},{"id":"2407.09726","title":"On Mitigating Code LLM Hallucinations with API Documentation","created":"2024-07-13","cited_by_count":21,"area":null},{"id":"2410.21157","title":"M2rc-Eval: Massively Multilingual Repository-level Code Completion Evaluation","created":"2024-10-28","cited_by_count":21,"area":null},{"id":"2412.11990","title":"ExecRepoBench: Multi-level Executable Code Completion Evaluation","created":"2024-12-16","cited_by_count":20,"area":null},{"id":"2410.20527","title":"CodeRosetta: Pushing the Boundaries of Unsupervised Code Translation for Parallel Programming","created":"2024-10-27","cited_by_count":19,"area":null},{"id":"2410.01353","title":"Codev-Bench: How Do LLMs Understand Developer-Centric Code Completion?","created":"2024-10-02","cited_by_count":18,"area":null},{"id":"2408.02193","title":"CodeACT: Code Adaptive Compute-efficient Tuning Framework for Code LLMs","created":"2024-08-05","cited_by_count":15,"area":null},{"id":"2408.02487","title":"LiCoEval: Evaluating LLMs on License Compliance in Code Generation","created":"2024-08-05","cited_by_count":14,"area":null},{"id":"2508.10111","title":"Constrained Decoding of Diffusion LLMs with Context-Free Grammars","created":"2025-08-13","cited_by_count":14,"area":null},{"id":"2411.13323","title":"Are Large Language Models Memorizing Bug Benchmarks?","created":"2024-11-20","cited_by_count":12,"area":null},{"id":"2407.13739","title":"Scaling Granite Code Models to 128K Context","created":"2024-07-18","cited_by_count":11,"area":null},{"id":"2410.11863","title":"ChatVis: Automating Scientific Visualization with a Large Language Model","created":"2024-10-07","cited_by_count":11,"area":null},{"id":"2503.00691","title":"How Diversely Can Language Models Solve Problems? Exploring the Algorithmic Diversity of Model-Generated Code","created":"2025-03-02","cited_by_count":11,"area":null},{"id":"2410.01791","title":"DreamGarden: A Designer Assistant for Growing Games from a Single Prompt","created":"2024-10-02","cited_by_count":10,"area":null},{"id":"2502.15680","title":"Privacy Ripple Effects from Adding or Removing Personal Information in Language Model Training","created":"2025-02-21","cited_by_count":10,"area":null},{"id":"2505.23657","title":"Active Layer-Contrastive Decoding Reduces Hallucination in Large Language Model Generation","created":"2025-05-29","cited_by_count":10,"area":null},{"id":"2507.10540","title":"FusionFactory: Fusing LLM Capabilities with Multi-LLM Log Data","created":"2025-07-14","cited_by_count":10,"area":null},{"id":"2410.04617","title":"Evaluation of Code LLMs on Geospatial Code Generation","created":"2024-10-06","cited_by_count":8,"area":null},{"id":"2502.07786","title":"Counterexample Guided Program Repair Using Zero-Shot Learning and MaxSAT-based Fault Localization","created":"2024-12-19","cited_by_count":8,"area":null},{"id":"2502.08806","title":"CLOVER: A Test Case Generation Benchmark with Coverage, Long-Context, and Verification","created":"2025-02-12","cited_by_count":8,"area":null},{"id":"2502.12598","title":"Bring Your Own Knowledge: A Survey of Methods for LLM Knowledge Expansion","created":"2025-02-18","cited_by_count":8,"area":null},{"id":"2503.18008","title":"Personalized Language Models via Privacy-Preserving Evolutionary Model Merging","created":"2025-03-23","cited_by_count":8,"area":null},{"id":"2508.00033","title":"GPT-4.1 Sets the Standard in Automated Experiment Design Using Novel Python Libraries","created":"2025-07-30","cited_by_count":8,"area":null},{"id":"2512.00020","title":"Large Language Model for Verilog Code Generation: Literature Review and the Road Ahead","created":"2025-10-29","cited_by_count":8,"area":null},{"id":"2410.07002","title":"CursorCore: Assist Programming through Aligning Anything","created":"2024-10-09","cited_by_count":7,"area":null},{"id":"2503.10452","title":"DynaCode: A Dynamic Complexity-Aware Code Benchmark for Evaluating Large Language Models in Code Generation","created":"2025-03-13","cited_by_count":7,"area":null},{"id":"2505.10443","title":"Are Large Language Models Robust in Understanding Code Against Semantics-Preserving Mutations?","created":"2025-05-15","cited_by_count":7,"area":null},{"id":"2408.04660","title":"XMainframe: A Large Language Model for Mainframe Modernization","created":"2024-08-05","cited_by_count":6,"area":null},{"id":"2411.05830","title":"GitChameleon: Unmasking the Version-Switching Capabilities of Code Generation Models","created":"2024-11-05","cited_by_count":6,"area":null},{"id":"2501.09653","title":"The Heap: A Contamination-Free Multilingual Code Dataset for Evaluating Large Language Models","created":"2025-01-16","cited_by_count":6,"area":null},{"id":"2503.05507","title":"Grammar-Based Code Representation: Is It a Worthy Pursuit for LLMs?","created":"2025-03-07","cited_by_count":5,"area":null},{"id":"2504.10557","title":"The Code Barrier: What LLMs Actually Understand?","created":"2025-04-14","cited_by_count":5,"area":null},{"id":"2504.12687","title":"Data-efficient LLM Fine-tuning for Code Generation","created":"2025-04-17","cited_by_count":5,"area":null},{"id":"2509.01082","title":"RefineStat: Efficient Exploration for Probabilistic Program Synthesis","created":"2025-09-01","cited_by_count":5,"area":null},{"id":"2407.08597","title":"Learning Program Behavioral Models from Synthesized Input-Output Pairs","created":"2024-07-11","cited_by_count":4,"area":null},{"id":"2408.14494","title":"Knowledge Graph Modeling-Driven Large Language Model Operating System (LLM OS) for Task Automation in Process Engineering Problem-Solving","created":"2024-08-23","cited_by_count":4,"area":null},{"id":"2410.17736","title":"MojoBench: Language Modeling and Benchmarks for Mojo","created":"2024-10-23","cited_by_count":4,"area":null},{"id":"2412.08859","title":"ViUniT: Visual Unit Tests for More Robust Visual Programming","created":"2024-12-12","cited_by_count":4,"area":null},{"id":"2502.06556","title":"MultiFileTest: A Multi-File-Level LLM Unit Test Generation Benchmark and Impact of Error Fixing Mechanisms","created":"2025-02-10","cited_by_count":4,"area":null},{"id":"2504.00019","title":"ObscuraCoder: Powering Efficient Code LM Pre-Training Via Obfuscation Grounding","created":"2025-03-27","cited_by_count":4,"area":null},{"id":"2601.12262","title":"Environment-Aware Code Generation: How far are We?","created":"2026-01-18","cited_by_count":4,"area":null},{"id":"2406.12326","title":"Towards Better Code Understanding in Decoder-Only Models with Contrastive Learning","created":"2024-06-18","cited_by_count":3,"area":null},{"id":"2410.07820","title":"Mitigating Gender Bias in Code Large Language Models via Model Editing","created":"2024-10-10","cited_by_count":3,"area":null},{"id":"2503.10737","title":"Commenting Higher-level Code Unit: Full Code, Reduced Code, or Hierarchical Code Summarization","created":"2025-03-13","cited_by_count":3,"area":null},{"id":"2503.22776","title":"Post-Incorporating Code Structural Knowledge into Pretrained Models via ICL for Code Translation","created":"2025-03-28","cited_by_count":3,"area":null},{"id":"2507.20783","title":"On The Role of Pretrained Language Models in General-Purpose Text Embeddings: A Survey","created":"2025-07-28","cited_by_count":3,"area":null},{"id":"2508.10074","title":"Next Edit Prediction: Learning to Predict Code Edits from Context and Interaction History","created":"2025-08-13","cited_by_count":3,"area":null},{"id":"2508.13975","title":"ChronoLLM: Customizing Language Models for Physics-Based Simulation Code Generation","created":"2025-08-19","cited_by_count":3,"area":null},{"id":"2510.06738","title":"AWM: Accurate Weight-Matrix Fingerprint for Large Language Models","created":"2025-10-08","cited_by_count":3,"area":null},{"id":"2510.23208","title":"Increasing LLM Coding Capabilities through Diverse Synthetic Coding Tasks","created":"2025-10-27","cited_by_count":3,"area":null},{"id":"2412.11699","title":"CoinMath: Harnessing the Power of Coding Instruction for Math LLMs","created":"2024-12-16","cited_by_count":2,"area":null},{"id":"2501.04510","title":"CGP-Tuning: Structure-Aware Soft Prompt Tuning for Code Vulnerability Detection","created":"2025-01-08","cited_by_count":2,"area":null},{"id":"2503.04241","title":"ThrowBench: Benchmarking LLMs by Predicting Runtime Exceptions","created":"2025-03-06","cited_by_count":2,"area":null},{"id":"2505.11441","title":"Is Compression Really Linear with Code Intelligence?","created":"2025-05-16","cited_by_count":2,"area":null},{"id":"2507.12642","title":"QSpark: Towards Reliable Qiskit Code Generation","created":"2025-07-16","cited_by_count":2,"area":null},{"id":"2601.05770","title":"Weights to Code: Extracting Interpretable Algorithms from the Discrete Transformer","created":"2026-01-09","cited_by_count":2,"area":null},{"id":"2602.02079","title":"AICD Bench: A Challenging Benchmark for AI-Generated Code Detection","created":"2026-02-02","cited_by_count":2,"area":null},{"id":"2408.09701","title":"Bridging the Language Gap: Enhancing Multilingual Prompt-Based Code Generation in LLMs via Zero-Shot Cross-Lingual Transfer","created":"2024-08-19","cited_by_count":1,"area":null},{"id":"2502.06854","title":"Can Large Language Models Understand Intermediate Representations in Compilers?","created":"2025-02-07","cited_by_count":1,"area":null},{"id":"2502.20246","title":"Beyond Natural Language Perplexity: Detecting Dead Code Poisoning in Code Generation Datasets","created":"2025-02-27","cited_by_count":1,"area":null},{"id":"2503.05840","title":"Slim attention: cut your context memory in half without loss -- K-cache is all you need for MHA","created":"2025-03-07","cited_by_count":1,"area":null},{"id":"2505.20505","title":"Large Language Models for IT Automation Tasks: Are We There Yet?","created":"2025-05-26","cited_by_count":1,"area":null},{"id":"2506.06069","title":"Zero-Shot Detection of LLM-Generated Code via Approximated Task Conditioning","created":"2025-06-06","cited_by_count":1,"area":null},{"id":"2506.20197","title":"Zero-Shot Attribution for Large Language Models: A Distribution Testing Approach","created":"2025-06-25","cited_by_count":1,"area":null},{"id":"2508.13948","title":"Prompt Orchestration Markup Language","created":"2025-08-19","cited_by_count":1,"area":null},{"id":"2510.08876","title":"Vector Graph-Based Repository Understanding for Issue-Driven File Retrieval","created":"2025-10-10","cited_by_count":1,"area":null},{"id":"2510.13697","title":"On Pretraining for Project-Level Code Completion","created":"2025-10-15","cited_by_count":1,"area":null},{"id":"2510.20975","title":"REx86: A Local Large Language Model for Assisting in x86 Assembly Reverse Engineering","created":"2025-10-23","cited_by_count":1,"area":null},{"id":"2512.02069","title":"Large Language Model based Smart Contract Auditing with LLMBugScanner","created":"2025-11-29","cited_by_count":1,"area":null},{"id":"2601.15879","title":"Evaluating and Achieving Controllable Code Completion in Code LLM","created":"2026-01-22","cited_by_count":1,"area":null},{"id":"2603.09951","title":"Towards a Neural Debugger for Python","created":"2026-03-10","cited_by_count":1,"area":null},{"id":"2409.13928","title":"Eliciting Instruction-tuned Code Language Models' Capabilities to Utilize Auxiliary Function for Code Generation","created":"2024-09-20","cited_by_count":0,"area":null},{"id":"2410.03137","title":"SAG: Style-Aligned Article Generation via Model Collaboration","created":"2024-10-04","cited_by_count":0,"area":null},{"id":"2412.03446","title":"From Words to Workflows: Automating Business Processes","created":"2024-12-04","cited_by_count":0,"area":null},{"id":"2503.06422","title":"GenAI for Simulation Model in Model-Based Systems Engineering","created":"2025-03-09","cited_by_count":0,"area":null},{"id":"2507.19904","title":"CrossPL: Evaluating Large Language Models on Cross Programming Language Code Generation","created":"2025-07-26","cited_by_count":0,"area":null},{"id":"2507.23178","title":"AutoBridge: Automating Smart Device Integration with Centralized Platform","created":"2025-07-31","cited_by_count":0,"area":null},{"id":"2509.12395","title":"Evaluating Large Language Models for Functional and Maintainable Code in Industrial Settings: A Case Study at ASML","created":"2025-09-15","cited_by_count":0,"area":null},{"id":"2510.13163","title":"A Matter of Representation: Towards Graph-Based Abstract Code Generation","created":"2025-10-15","cited_by_count":0,"area":null},{"id":"2511.04538","title":"From Model to Breach: Towards Actionable LLM-Generated Vulnerabilities Reporting","created":"2025-11-06","cited_by_count":0,"area":null},{"id":"2512.11402","title":"REMODEL-LLM: Transforming C code to Java using LLMs","created":"2025-12-12","cited_by_count":0,"area":null},{"id":"2604.01849","title":"From Guessing to Placeholding: A Cost-Theoretic Framework for Uncertainty-Aware Code Completion","created":"2026-04-02","cited_by_count":0,"area":null},{"id":"2604.19826","title":"Co-Located Tests, Better AI Code: How Test Syntax Structure Affects Foundation Model Code Generation","created":"2026-04-20","cited_by_count":0,"area":null},{"id":"2604.21716","title":"From If-Statements to ML Pipelines: Revisiting Bias in Code-Generation","created":"2026-04-23","cited_by_count":0,"area":null},{"id":"2604.27551","title":"Beyond the Training Distribution: Mapping Generalization Boundaries in Neural Program Synthesis","created":"2026-04-30","cited_by_count":0,"area":null},{"id":"2606.03128","title":"Decoupled Smart Contract Audits: Lightweight LLM Framework via Distillation and Aggregation","created":"2026-06-02","cited_by_count":0,"area":null},{"id":"2606.07999","title":"Efficient Skill Grounding via Code Refactoring with Small Language Models","created":"2026-06-06","cited_by_count":0,"area":null},{"id":"2606.24901","title":"LLM Evolution as an Industry-Scale Ecosystem: A Lifecycle Perspective on Continual Learning","created":"2026-06-12","cited_by_count":0,"area":null},{"id":"2607.07881","title":"Functional and Secure Code Generation with Task Vectors","created":"2026-07-08","cited_by_count":0,"area":null},{"id":"2610.19157","title":"DivAlgo: A systematic evaluation of algorithmic diversity for code generation models","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}