Papers Code Generation
“Code Generation” 태그가 달린 논문 3,075편 · 필터 해제
Distilled Continuous Diffusion Language Models Can Write Code in Few Steps---or One
Language generation is almost universally treated as a sequential process: autoregressive models emit one token at a time, while diffusion language models replace token-level seriality with a long trajectory of iterative…
Code GenerationPaperCompiler: Faithful Paper-to-Code Generation via Repository-Level Specification Compilation
Faithfully translating research papers into repository-level implementations remains challenging because papers often describe methods at a high level, leave implementation assumptions implicit, and require generated rep…
Code GenerationExecRetrieval: Measuring the Functional-Correctness Gap in Code-Embedding Retrieval
Embedding-based code retrieval is a core component of coding agents and retrieval-augmented code generation, where retrieving correct code matters more than retrieving lexically similar code. Existing code-retrieval benc…
Code GenerationHidden Threat in Synthetic Data: Covert Targeted Bias Injection through Benign Text
Synthetic data is increasingly used to train large language models (LLMs), yet its security implications remain poorly understood. Prior work on subliminal learning suggests that models can inherit behavioral traits from…
Code GenerationDARTS: Decoder-Aware Representation Tuning via Surgery for Model Merging
Model merging combines multiple task-specific fine-tuned LLMs into a single multi-task model without additional training. However, merged models are known to suffer from representation bias: systematic drift between the …
Mathematical ReasoningInstruction FollowingCode GenerationRubric-to-Code Credit Assignment for Reinforcement Learning
Interactive web application generation requires models to produce usable HTML, CSS, and JavaScript applications from natural language requests. Unlike conventional code generation, application quality depends on multiple…
Reinforcement LearningCode GenerationProgRouter: Online Progress-Guided Orchestration for Multi-Agent LLM Workflows under Quality-Cost Tradeoffs
Multi-agent large language model (LLM) workflows have emerged as a powerful paradigm for solving complex, open-ended tasks through collaborative reasoning among specialized LLM agents, but they incur substantial operatin…
Mathematical ReasoningQuestion AnsweringCode GenerationMACGen: Toward Functionally Correct and Secure Code Generation via Multi-Agent Collaboration
Despite their strong ability to generate code, large language models often fail to produce secure code, as their outputs frequently contain security vulnerabilities. Secure code generation is inherently challenging becau…
Code GenerationRubrics as Visual-Repair Context for Self-Evolving UI-to-Code Generation
Large vision-language models have shown strong progress in UI-to-code generation, yet their test-time self-evolution remains unstable. We first identify a fundamental obstacle, termed visual repair coupling: a local code…
Code GenerationCan Coding Agents Build Robust Baselines? A Skill-Based Approach for Automating the Medical Imaging Model-Development Pipeline
Developing competitive deep learning baselines for medical imaging remains a highly iterative process requiring literature review, implementation, experimentation, and expert refinement. Existing automation approaches ty…
Domain GeneralizationCode GenerationLongWoF-Bench: Evaluating EvoMap Genes for Verifiable Long-Workflow Tasks
Large language models are increasingly expected to execute complex workflows whose success depends on maintaining interdependent constraints and producing artifacts that satisfy strict end-to-end verification. Yet succes…
Mathematical ReasoningCode GenerationMARS: Multi-Specialist LLM Relay System for Competitive Programming
Large Language Models excel at code generation, yet competitive programming exposes a persistent failure mode: existing multi-agent pipelines distribute work over generic planner, coder, and debugger roles and delegate t…
Code GenerationTESTNAV: Pareto-Guided Search for Compositional Robustness Testing
Deep learning models remain vulnerable to real-world input perturbations, especially when multiple corruptions co-occur in the same input (e.g., brightness shifts and motion blur). Compositional testing reveals these int…
Code GenerationRepo0: Design-Driven Zero-to-All Code Generation
Large language model agents have made substantial progress in code generation, yet most existing systems assume a predefined repository architecture. This assumption does not hold in zero-to-all code generation, where an…
Code GenerationGrading the Graders: Verification Autonomy Levels (L0-L5) for LLM Reasoning
Large language models (LLMs) are increasingly paired with verifiers (step checkers, self-consistency filters, tool-based fact checkers, formal proof assistants) that claim to detect the model's errors. Yet the verificati…
Medical DiagnosisCode GenerationSemaPLC: A Project-Grounded, Verification-Gated Agent Harness for PLC Code Generation
Programmable logic controllers (PLCs) run industrial plants, and large language models can already generate independent program organization units (POUs) for them. Whether such logic integrates into an existing PLC proje…
Code GenerationLLM as Detector: An In-context Learning Approach for Tabular Anomaly Detection
Anomaly detection in tabular data is challenging because abnormal samples often arise as violations of cross-feature dependencies rather than simple marginal deviations. Existing detectors rely on geometric or reconstruc…
Anomaly DetectionCode GenerationTokEval: A Tokenizer Evaluation Suite
Language model tokenizers are typically selected with minimal evaluation, despite the fact that their design choices directly impact model capabilities. This can be partly attributed to a limited understanding of which t…
Mathematical ReasoningCode GenerationA Comprehensive Review of Large Language Models for Nanophotonics: From Surrogate Modeling to Autonomous Design
Metasurfaces have revolutionized the development of photonic devices by enabling unprecedented precision in light manipulation. However, their design processes are often constrained by computationally expensive simulatio…
Code GenerationWhen State Becomes an Attack Surface: State-Semantic Injection in LLM-Driven Embodied Agents
Large Language Models (LLMs) have demonstrated capabilities in in-context learning, task decomposition, step-by-step reasoning, and code generation, driving their gradual evolution from text generation models into the co…
Text GenerationCode Generation