Papers Code Generation
“Code Generation” 태그가 달린 논문 3,075편 · 필터 해제
An Online Reference-Free Evaluation Framework for Flowchart Image-to-Code Generation
Vision-Language Models (VLMs) are increasingly used in document processing pipelines to convert flowchart images into structured code (e.g., Mermaid). In production, these systems process arbitrary inputs for which no gr…
Visual EntailmentCode GenerationNanbeige4.1-3B: A Small General Model that Reasons, Aligns, and Acts
We present Nanbeige4.1-3B, a unified generalist language model that simultaneously achieves strong agentic behavior, code generation, and general reasoning with only 3B parameters. To the best of our knowledge, it is the…
Reinforcement LearningCode GenerationLLM-Driven 3D Scene Generation of Agricultural Simulation Environments
Procedural generation techniques in 3D rendering engines have revolutionized the creation of complex environments, reducing reliance on manual design. Recent approaches using Large Language Models (LLMs) for 3D scene gen…
Scene GenerationCode GenerationDICE: Diffusion Large Language Models Excel at Generating CUDA Kernels
Diffusion large language models (dLLMs) have emerged as a compelling alternative to autoregressive (AR) LLMs, owing to their capacity for parallel token generation. This paradigm is particularly well-suited for code gene…
Reinforcement LearningCode GenerationCode2Worlds: Empowering Coding LLMs for 4D World Generation
Achieving spatial intelligence requires moving beyond visual plausibility to build world simulators grounded in physical laws. While coding LLMs have advanced static 3D scene generation, extending this paradigm to 4D dyn…
Scene GenerationCode GenerationImproving HPC Code Generation Capability of LLMs via Online Reinforcement Learning with Real-Machine Benchmark Rewards
Large language models (LLMs) have demonstrated strong code generation capabilities, yet the runtime performance of generated code is not guaranteed, and there have been few attempts to train LLMs using runtime performanc…
Reinforcement LearningCode GenerationPerceptual Self-Reflection in Agentic Physics Simulation Code Generation
We present a multi-agent framework for generating physics simulation code from natural language descriptions, featuring a novel perceptual self-reflection mechanism for validation. The system employs four specialized age…
Code GenerationLearning beyond Teacher: Generalized On-Policy Distillation with Reward Extrapolation
On-policy distillation (OPD), which aligns the student with the teacher's logit distribution on student-generated trajectories, has demonstrated strong empirical gains in improving student performance and often outperfor…
Reinforcement LearningCode GenerationVESPO: Variational Sequence-Level Soft Policy Optimization for Stable Off-Policy LLM Training
Off-policy updates are inevitable in reinforcement learning (RL) for large language models (LLMs) due to rollout staleness from asynchronous training and mismatches between training and inference engines. Naive importanc…
Reinforcement LearningCode GenerationTraining and Benchmarking Code Generation for Physics-Inspired Animations
Large language models (LLMs) have been widely studied in areas such as mathematical reasoning, complex coding, and scientific problem solving. However, their ability to generate executable code that visually depicts phys…
Reinforcement LearningCode GenerationChart Specification: Structural Representations for Incentivizing VLM Reasoning in Chart-to-Code Generation
Vision-Language Models (VLMs) have shown promise in generating plotting code from chart images, yet achieving structural fidelity remains challenging. Existing approaches largely rely on supervised fine-tuning, encouragi…
Reinforcement LearningCode GenerationSearch or Accelerate: Confidence-Switched Position Beam Search for Diffusion Language Models
Diffusion Language Models (DLMs) generate text by iteratively denoising a masked sequence, repeatedly deciding which positions to commit at each step. Standard decoding follows a greedy rule: unmask the most confident po…
Mathematical ReasoningCode GenerationCompressed Sensing for Capability Localization in Large Language Models
Large language models (LLMs) exhibit a wide range of capabilities, including mathematical reasoning, code generation, and linguistic behaviors. We show that Transformer architectures contain small subsets of attention he…
Mathematical ReasoningCode GenerationFine-Tuning GPT-5 for GPU Kernel Generation
Developing efficient GPU kernels is essential for scaling modern AI systems, yet it remains a complex task due to intricate hardware architectures and the need for specialized optimization expertise. Although Large Langu…
Reinforcement LearningCode GenerationSiliconMind-V1: Multi-Agent Distillation and Debug-Reasoning Workflows for Verilog Code Generation
Large language models (LLMs) have recently emerged as a promising approach for automating Verilog code generation; however, existing methods primarily emphasize syntactic correctness and often rely on commercial models o…
Code GenerationAlgoVeri: An Aligned Benchmark for Verified Code Generation on Classical Algorithms
Vericoding refers to the generation of formally verified code from rigorous specifications. Recent AI models show promise in vericoding, but a unified methodology for cross-paradigm evaluation is lacking. Existing benchm…
Code GenerationListen to the Layers: Mitigating Hallucinations with Inter-Layer Disagreement
Pretrained Large Language Models (LLMs) are prone to generating fluent yet factually incorrect text-a phenomenon known as hallucinations, undermining their reliability and utility in downstream tasks. We hypothesize that…
Mathematical ReasoningCode GenerationOn the Optimal Reasoning Length for RL-Trained Language Models
Reinforcement learning substantially improves reasoning in large language models, but it also tends to lengthen chain-of-thought outputs and increase computational cost. Although length-control methods have been proposed…
Reinforcement LearningMathematical ReasoningCode GenerationEvoCodeBench: A Human-Performance Benchmark for Self-Evolving LLM-Driven Coding Systems
As large language models (LLMs) continue to advance in programming tasks, LLM-driven coding systems have evolved from one-shot code generation into complex systems capable of iterative improvement during inference. Howev…
Code GenerationKernelCraft: Benchmarking for Agentic Close-to-Metal Kernel Generation on Emerging Hardware
New AI accelerators with novel instruction set architectures (ISAs) often require developers to manually craft low-level kernels, a time-consuming and error-prone process that does not scale across hardware targets. This…
Code Generation