代码生成论文趋势 2023–2026

程序合成与代码 LLM

统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 2,161 篇被归入该主题的论文。

主要结论

每年论文数

各会议论文数

按年份和会议统计

代码生成论文数，按年份和会议
年份NeurIPSICLRICMLCVPR合计
202329553195210
202413566111134446
202523016479172645
2026236241174209860

代表论文

按年份和会议均匀挑选，方便快速看到每一届的样貌

全部代码生成论文

年份全部2023202420252026
会议全部NeurIPSICLRICMLCVPR

共 645 篇，第 4 / 13 页

  1. CVPR 2025TexGarment: Consistent Garment UV Texture Generation via Efficient 3D Structure-Guided Diffusion Transformer
  2. CVPR 2025TFCustom: Customized Image Generation with Time-Aware Frequency Feature Guidance
  3. CVPR 2025Three-view Focal Length Recovery From Homographies
  4. CVPR 2025TIMotion: Temporal and Interactive Framework for Efficient Human-Human Motion Generation
  5. CVPR 2025TKG-DM: Training-free Chroma Key Content Generation Diffusion Model
  6. CVPR 2025TokenFlow: Unified Image Tokenizer for Multimodal Understanding and Generation
  7. CVPR 2025TopoCellGen: Generating Histopathology Cell Topology with a Diffusion Model
  8. CVPR 2025Tora: Trajectory-oriented Diffusion Transformer for Video Generation
  9. CVPR 2025Towards Transformer-Based Aligned Generation with Self-Coherence Guidance
  10. CVPR 2025Towards Unbiased and Robust Spatio-Temporal Scene Graph Generation and Anticipation
  11. CVPR 2025Towards Understanding and Quantifying Uncertainty for Text-to-Image Generation
  12. CVPR 2025TreeMeshGPT: Artistic Mesh Generation with Autoregressive Tree Sequencing
  13. CVPR 2025Type-R: Automatically Retouching Typos for Text-to-Image Generation
  14. CVPR 2025UniPose: A Unified Multimodal Framework for Human Pose Comprehension, Generation and Editing
  15. CVPR 2025UniScene: Unified Occupancy-centric Driving Scene Generation
  16. CVPR 2025Universal Scene Graph Generation
  17. CVPR 2025Unseen Visual Anomaly Generation
  18. CVPR 2025VIRES: Video Instance Repainting via Sketch and Text Guided Generation
  19. CVPR 2025Volumetrically Consistent 3D Gaussian Rasterization
  20. CVPR 2025WISNet: Pseudo Label Generation on Unbalanced and Patch Annotated Waste Images
  21. CVPR 2025WonderWorld: Interactive 3D Scene Generation from a Single Image
  22. CVPR 2025ZoomLDM: Latent Diffusion Model for Multi-scale Image Generation
  23. ICLR 20253DIS: Depth-Driven Decoupled Image Synthesis for Universal Multi-Instance Generation
  24. ICLR 2025A Simple Approach to Unifying Diffusion-based Conditional Generation
  25. ICLR 2025A Theory for Token-Level Harmonization in Retrieval-Augmented Generation
  26. ICLR 2025Accelerating Auto-regressive Text-to-Image Generation with Training-free Speculative Jacobi Decoding
  27. ICLR 2025Accelerating Inference of Retrieval-Augmented Generation via Sparse Context Selection
  28. ICLR 2025Adaptive Deployment of Untrusted LLMs Reduces Distributed Threats
  29. ICLR 2025Adding Conditional Control to Diffusion Models with Reinforcement Learning
  30. ICLR 2025Advancing Graph Generation through Beta Diffusion
  31. ICLR 2025AFlow: Automating Agentic Workflow Generation
  32. ICLR 2025Aligning Human Motion Generation with Human Perceptions
  33. ICLR 2025An Engorgio Prompt Makes Large Language Model Babble on
  34. ICLR 2025APE: Faster and Longer Context-Augmented Generation via Adaptive Parallel Encoding
  35. ICLR 2025API Pack: A Massive Multi-Programming Language Dataset for API Call Generation
  36. ICLR 2025Automated Proof Generation for Rust Code via Self-Evolution
  37. ICLR 2025Backtracking Improves Generation Safety
  38. ICLR 2025Benchmarking Agentic Workflow Generation
  39. ICLR 2025Beyond Autoregression: Fast LLMs via Self-Distillation Through Time
  40. ICLR 2025BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions
  41. ICLR 2025BigDocs: An Open Dataset for Training Multimodal Models on Document and Code Tasks
  42. ICLR 2025BOND: Aligning LLMs with Best-of-N Distillation
  43. ICLR 2025Calibrating LLMs with Information-Theoretic Evidential Deep Learning
  44. ICLR 2025Can LLMs Generate Novel Research Ideas? A Large-Scale Human Study with 100+ NLP Researchers
  45. ICLR 2025ChartMimic: Evaluating LMM's Cross-Modal Reasoning Capability via Chart-to-Code Generation
  46. ICLR 2025ChatQA 2: Bridging the Gap to Proprietary LLMs in Long Context and RAG Capabilities
  47. ICLR 2025ClimaQA: An Automated Evaluation Framework for Climate Question Answering Models
  48. ICLR 2025CodePlan: Unlocking Reasoning Potential in Large Language Models by Scaling Code-form Planning
  49. ICLR 2025Commit0: Library Generation from Scratch
  50. ICLR 2025Context Steering: Controllable Personalization at Inference Time

在 Claude、Cursor 里直接问这个趋势

接上 Paperlist MCP 后，写综述、挑方向或准备投稿时，不用离开对话框就能拿到这页的数字：每年各会议的论文数、增长倍数、涨得最快的子方向和代表论文，AI 会按你的问题整理。

可以直接复制这句话问 AI

用 paperlist 查代码生成在 NeurIPS 2023–2026 的论文趋势，哪一年涨得最快？

AI 会调用的工具：get_topic_stats {"topic": "code-generation"}

两分钟接入 Paperlist MCP（Claude Code、Cursor、Codex、ChatGPT）

常见问题

2023–2026 年四大会议一共有多少篇代码生成论文？
共 2,161 篇，按年份分别是 2023 年 210 篇、2024 年 446 篇、2025 年 645 篇、2026 年 860 篇。
NeurIPS 2026 有多少篇代码生成论文？
NeurIPS 2026 有 236 篇代码生成论文，上一届是 230 篇。
ICLR 2026 有多少篇代码生成论文？
ICLR 2026 有 241 篇代码生成论文，上一届是 164 篇。
ICML 2026 有多少篇代码生成论文？
ICML 2026 有 174 篇代码生成论文，上一届是 79 篇。
CVPR 2026 有多少篇代码生成论文？
CVPR 2026 有 209 篇代码生成论文，上一届是 172 篇。
哪个会议的代码生成论文最多？
NeurIPS，2023–2026 年共 630 篇。

「自然语言」下的其他主题