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 526 篇，第 6 / 11 页

  1. ICLR 2025Aligning Human Motion Generation with Human Perceptions
  2. ICLR 2025An Engorgio Prompt Makes Large Language Model Babble on
  3. ICLR 2025APE: Faster and Longer Context-Augmented Generation via Adaptive Parallel Encoding
  4. ICLR 2025API Pack: A Massive Multi-Programming Language Dataset for API Call Generation
  5. ICLR 2025Automated Proof Generation for Rust Code via Self-Evolution
  6. ICLR 2025Backtracking Improves Generation Safety
  7. ICLR 2025Benchmarking Agentic Workflow Generation
  8. ICLR 2025Beyond Autoregression: Fast LLMs via Self-Distillation Through Time
  9. ICLR 2025BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions
  10. ICLR 2025BigDocs: An Open Dataset for Training Multimodal Models on Document and Code Tasks
  11. ICLR 2025BOND: Aligning LLMs with Best-of-N Distillation
  12. ICLR 2025Calibrating LLMs with Information-Theoretic Evidential Deep Learning
  13. ICLR 2025Can LLMs Generate Novel Research Ideas? A Large-Scale Human Study with 100+ NLP Researchers
  14. ICLR 2025ChartMimic: Evaluating LMM's Cross-Modal Reasoning Capability via Chart-to-Code Generation
  15. ICLR 2025ChatQA 2: Bridging the Gap to Proprietary LLMs in Long Context and RAG Capabilities
  16. ICLR 2025ClimaQA: An Automated Evaluation Framework for Climate Question Answering Models
  17. ICLR 2025CodePlan: Unlocking Reasoning Potential in Large Language Models by Scaling Code-form Planning
  18. ICLR 2025Commit0: Library Generation from Scratch
  19. ICLR 2025Context Steering: Controllable Personalization at Inference Time
  20. ICLR 2025ControlAR: Controllable Image Generation with Autoregressive Models
  21. ICLR 2025Controllable Generation via Locally Constrained Resampling
  22. ICLR 2025ConvCodeWorld: Benchmarking Conversational Code Generation in Reproducible Feedback Environments
  23. ICLR 2025Copyright-Protected Language Generation via Adaptive Model Fusion
  24. ICLR 2025CoRNStack: High-Quality Contrastive Data for Better Code Retrieval and Reranking
  25. ICLR 2025Correlation and Navigation in the Vocabulary Key Representation Space of Language Models
  26. ICLR 2025CraftRTL: High-quality Synthetic Data Generation for Verilog Code Models with Correct-by-Construction Non-Textual Representations and Targeted Code Repair
  27. ICLR 2025CubeDiff: Repurposing Diffusion-Based Image Models for Panorama Generation
  28. ICLR 2025DataGen: Unified Synthetic Dataset Generation via Large Language Models
  29. ICLR 2025DAWN: Dynamic Frame Avatar with Non-autoregressive Diffusion Framework for Talking head Video Generation
  30. ICLR 2025DeepRTL: Bridging Verilog Understanding and Generation with a Unified Representation Model
  31. ICLR 2025Diffusing to the Top: Boost Graph Neural Networks with Minimal Hyperparameter Tuning
  32. ICLR 2025Diffusion On Syntax Trees For Program Synthesis
  33. ICLR 2025Diffusion-based Neural Network Weights Generation
  34. ICLR 2025DiscoveryBench: Towards Data-Driven Discovery with Large Language Models
  35. ICLR 2025Discrete Distribution Networks
  36. ICLR 2025Drop-Upcycling: Training Sparse Mixture of Experts with Partial Re-initialization
  37. ICLR 2025DynamicCity: Large-Scale 4D Occupancy Generation from Dynamic Scenes
  38. ICLR 2025ECHOPulse: ECG Controlled Echocardio-gram Video Generation
  39. ICLR 2025Emerging Safety Attack and Defense in Federated Instruction Tuning of Large Language Models
  40. ICLR 2025ESE: Espresso Sentence Embeddings
  41. ICLR 2025Execution-guided within-prompt search for programming-by-example
  42. ICLR 2025Explore Theory of Mind: program-guided adversarial data generation for theory of mind reasoning
  43. ICLR 2025FaithEval: Can Your Language Model Stay Faithful to Context, Even If "The Moon is Made of Marshmallows"
  44. ICLR 2025Fast Direct: Query-Efficient Online Black-box Guidance for Diffusion-model Target Generation
  45. ICLR 2025FlexCAD: Unified and Versatile Controllable CAD Generation with Fine-tuned Large Language Models
  46. ICLR 2025Forking Paths in Neural Text Generation
  47. ICLR 2025FreCaS: Efficient Higher-Resolution Image Generation via Frequency-aware Cascaded Sampling
  48. ICLR 2025FreeVS: Generative View Synthesis on Free Driving Trajectory
  49. ICLR 2025From Few to Many: Self-Improving Many-Shot Reasoners Through Iterative Optimization and Generation
  50. ICLR 2025GALA: Geometry-Aware Local Adaptive Grids for Detailed 3D Generation

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