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 11 / 13 页

  1. NeurIPS 2025FuncGenFoil: Airfoil Generation and Editing Model in Function Space
  2. NeurIPS 2025Fused View-Time Attention and Feedforward Reconstruction for 4D Scene Generation
  3. NeurIPS 2025Generating Computational Cognitive models using Large Language Models
  4. NeurIPS 2025GeoCAD: Local Geometry-Controllable CAD Generation with Large Language Models
  5. NeurIPS 2025GPSToken: Gaussian Parameterized Spatially-adaptive Tokenization for Image Representation and Generation
  6. NeurIPS 2025Greed is Good: A Unifying Perspective on Guided Generation
  7. NeurIPS 2025HairFree: Compositional 2D Head Prior for Text-Driven 360° Bald Texture Synthesis
  8. NeurIPS 2025Hawk: Leveraging Spatial Context for Faster Autoregressive Text-to-Image Generation
  9. NeurIPS 2025HBLLM: Wavelet-Enhanced High-Fidelity 1-Bit Quantization for LLMs
  10. NeurIPS 2025Hierarchical Koopman Diffusion: Fast Generation with Interpretable Diffusion Trajectory
  11. NeurIPS 2025HiFlow: Training-free High-Resolution Image Generation with Flow-Aligned Guidance
  12. NeurIPS 2025Hogwild! Inference: Parallel LLM Generation via Concurrent Attention
  13. NeurIPS 2025HyPlaneHead: Rethinking Tri-plane-like Representations in Full-Head Image Synthesis
  14. NeurIPS 2025Improving Regret Approximation for Unsupervised Dynamic Environment Generation
  15. NeurIPS 2025Improving the Euclidean Diffusion Generation of Manifold Data by Mitigating Score Function Singularity
  16. NeurIPS 2025Inference-Time Scaling for Flow Models via Stochastic Generation and Rollover Budget Forcing
  17. NeurIPS 2025Influence Guided Context Selection for Effective Retrieval-Augmented Generation
  18. NeurIPS 2025InstanceAssemble: Layout-Aware Image Generation via Instance Assembling Attention
  19. NeurIPS 2025InstructFlow: Adaptive Symbolic Constraint-Guided Code Generation for Long-Horizon Planning
  20. NeurIPS 2025IntrinsiX: High-Quality PBR Generation using Image Priors
  21. NeurIPS 2025Joint Relational Database Generation via Graph-Conditional Diffusion Models
  22. NeurIPS 2025Keep It on a Leash: Controllable Pseudo-label Generation Towards Realistic Long-Tailed Semi-Supervised Learning
  23. NeurIPS 2025KVLink: Accelerating Large Language Models via Efficient KV Cache Reuse
  24. NeurIPS 2025KVzip: Query-Agnostic KV Cache Compression with Context Reconstruction
  25. NeurIPS 2025Large Language Diffusion Models
  26. NeurIPS 2025Lessons Learned: A Multi-Agent Framework for Code LLMs to Learn and Improve
  27. NeurIPS 2025Let's Revise Step-by-Step: A Unified Local Search Framework for Code Generation with LLMs
  28. NeurIPS 2025LeVo: High-Quality Song Generation with Multi-Preference Alignment
  29. NeurIPS 2025Limited Preference Data? Learning Better Reward Model with Latent Space Synthesis
  30. NeurIPS 2025LLM Meets Diffusion: A Hybrid Framework for Crystal Material Generation
  31. NeurIPS 2025LMFusion: Adapting Pretrained Language Models for Multimodal Generation
  32. NeurIPS 2025Machine Unlearning in 3D Generation: A Perspective-Coherent Acceleration Framework
  33. NeurIPS 2025Magical: Medical Lay Language Generation via Semantic Invariance and Layperson-tailored Adaptation
  34. NeurIPS 2025MaintainCoder: Maintainable Code Generation Under Dynamic Requirements
  35. NeurIPS 2025Matching Markets Meet LLMs: Algorithmic Reasoning with Ranked Preferences
  36. NeurIPS 2025Matryoshka Pilot: Learning to Drive Black-Box LLMs with LLMs
  37. NeurIPS 2025MEGADance: Mixture-of-Experts Architecture for Genre-Aware 3D Dance Generation
  38. NeurIPS 2025MeshCoder: LLM-Powered Structured Mesh Code Generation from Point Clouds
  39. NeurIPS 2025MetaDefense: Defending Fine-tuning based Jailbreak Attack Before and During Generation
  40. NeurIPS 2025Metis: A Foundation Speech Generation Model with Masked Generative Pre-training
  41. NeurIPS 2025MigGPT: Harnessing Large Language Models for Automated Migration of Out-of-Tree Linux Kernel Patches Across Versions
  42. NeurIPS 2025Mind the Quote: Enabling Quotation-Aware Dialogue in LLMs via Plug-and-Play Modules
  43. NeurIPS 2025MIND: Material Interface Generation from UDFs for Non-Manifold Surface Reconstruction
  44. NeurIPS 2025Mixture of Inputs: Text Generation Beyond Discrete Token Sampling
  45. NeurIPS 2025More Than Generation: Unifying Generation and Depth Estimation via Text-to-Image Diffusion Models
  46. NeurIPS 2025More Than Just Functional: LLM-as-a-Critique for Efficient Code Generation
  47. NeurIPS 2025Multiverse: Your Language Models Secretly Decide How to Parallelize and Merge Generation
  48. NeurIPS 2025Neither Valid nor Reliable? Investigating the Use of LLMs as Judges
  49. NeurIPS 2025NeuroGenPoisoning: Neuron-Guided Attacks on Retrieval-Augmented Generation of LLM via Genetic Optimization of External Knowledge
  50. NeurIPS 2025NeuroPath: Neurobiology-Inspired Path Tracking and Reflection for Semantically Coherent Retrieval

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