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 860 篇，第 14 / 18 页

  1. NeurIPS 2026BrickAnything: Geometry-Conditioned Buildable Brick Generation with Structure-Aware Tokenization
  2. NeurIPS 2026Bridging Diffusion and Autoregression for Flexible Time Series Synthesis
  3. NeurIPS 2026Can Bits Seal Language?
  4. NeurIPS 2026Can LLMs Take Retrieved Information with a Grain of Salt?
  5. NeurIPS 2026CASL-VAE: Learning Structured Latent Variables from Unpaired Data for Semi-supervised Clustering and Paired Sample Generation
  6. NeurIPS 2026ChronosAlign: A Large-Scale, Updatable Benchmark for Decomposing Temporal Alignment in LLMs
  7. NeurIPS 2026CME–SpectrumBench: Can LLMs Analyze Condensed Matter Spectral Data?
  8. NeurIPS 2026CodeScaler: Scaling Code LLM Training and Test-Time Inference via Reward Models
  9. NeurIPS 2026CogBench: Evaluating Cognitive-Level Control in LLM Question Generation
  10. NeurIPS 2026CoilStellaration: A Dataset and Benchmark for Engineering-Aware Stellarator Coilset Generation
  11. NeurIPS 2026Conflict-Suppressed RAG: A Simple Decoding-Time Framework for Faithful Retrieval-Augmented Generation
  12. NeurIPS 2026ConQuR: Corner Aligned Activation Quantization via Optimized Rotations for LLMs
  13. NeurIPS 2026Constrained Goal-directed Planar Graph Generation with Grammar-based Reinforcement Learning
  14. NeurIPS 2026Continuous Latent Diffusion Language Model
  15. NeurIPS 2026Contrastive Identification and Generation in the Limit
  16. NeurIPS 2026Contrastive Thinking Decoding: Steering Answer Generation in Reasoning Models
  17. NeurIPS 2026Coreset-Induced Conditional Velocity Flow Matching
  18. NeurIPS 2026Corrective Diffusion Language Models
  19. NeurIPS 2026Correpondence Alignment For Improved Virtual Try-On
  20. NeurIPS 2026Coupling Models for One-Step Discrete Generation
  21. NeurIPS 2026CRISP: Fixing Flying Pixels in Latent LiDAR Generation via Diffusion Decoding
  22. NeurIPS 2026CryptanalysisBench: Can LLMs do cryptanalysis?
  23. NeurIPS 2026Curriculum proof repair with learned counterexamples
  24. NeurIPS 2026CyCLeGen: Cycle-Consistent Layout Prediction and Image Generation
  25. NeurIPS 2026Debiased Counterfactual Generation via Flow Matching from Observations
  26. NeurIPS 2026DeepfakeGenome: Toward Next-Generation Deepfake Attribution
  27. NeurIPS 2026Dependency-Guided Parallel Decoding in Discrete Diffusion Language Models
  28. NeurIPS 2026DialectLLM: A Dialect-Aware Dialog[ue] Generation Framework Beyond Standard American English
  29. NeurIPS 2026Differentiable Retrieval-Augmented Generation for Predicting Cellular Responses to Gene Perturbation
  30. NeurIPS 2026Diffusion Language Models Can Approximate Optimal Infilling Lengths Implicitly
  31. NeurIPS 2026DiPhon: Diffusion on Graphons for Scalable Graph Generation
  32. NeurIPS 2026DiReCL: Learning Differentiable Reward Code with Inverse Reinforcement Learning
  33. NeurIPS 2026DIS-Bench: Evaluating LLMs on System Testing via Directed Input Synthesis
  34. NeurIPS 2026Discrete Stochastic Localization for Non-autoregressive Generation
  35. NeurIPS 2026Disentangling Dual Image References in Frequency Aware Diffusion Models for Personalized Generation
  36. NeurIPS 2026Does Your Large Language Model Have An Intuitive Sense of The Difficulty of A Question?
  37. NeurIPS 2026Doomed to Re-Annotate, Forever: The ImageNet Story
  38. NeurIPS 2026dRAE: Representation Autoencoder with Hyper-Spherical Codes
  39. NeurIPS 2026DriftWeight: Repulsive Drift in Mean-Flow Space for Neural Network Weight Generation
  40. NeurIPS 2026DRTriton: Large-Scale Synthetic Data Driven Reinforcement Learning for Triton Kernel Generation
  41. NeurIPS 2026Duality Models: An Embarrassingly Simple One-step Generation Paradigm
  42. NeurIPS 2026Dynamic Video Generation: Shaping Video Generation Across Time and Space
  43. NeurIPS 2026EditFlowSR: Revisable Expression Generation for Symbolic Regression
  44. NeurIPS 2026ELSA3D: Elastic Semantic Anchoring for Unified 3D Understanding and Generation
  45. NeurIPS 2026Empirical regularities in subjective decision-making by LLMs
  46. NeurIPS 2026Enhancing Agentic Code Localization with Traceability Recovered from Repository Evolution
  47. NeurIPS 2026Epiplexity Guided Data Selection and Generation for Out-of-Distribution Generalization
  48. NeurIPS 2026Evaluating Whether LLMs Can Reliably Connect the DOTs?
  49. NeurIPS 2026EvoOptiGraph: Weakness-Driven Coevolution via Graph-Based Structural Generation for Optimization Modeling
  50. NeurIPS 2026Exact Regular-Constrained Sampling for Variable-Order Markov 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