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 630 篇，第 12 / 13 页

  1. NeurIPS 2024MILP-StuDio: MILP Instance Generation via Block Structure Decomposition
  2. NeurIPS 2024MSA Generation with Seqs2Seqs Pretraining: Advancing Protein Structure Predictions
  3. NeurIPS 2024Natural Counterfactuals With Necessary Backtracking
  4. NeurIPS 2024Nearest Neighbor Speculative Decoding for LLM Generation and Attribution
  5. NeurIPS 2024Neural Residual Diffusion Models for Deep Scalable Vision Generation
  6. NeurIPS 2024NovoBench: Benchmarking Deep Learning-based \emph{De Novo} Sequencing Methods in Proteomics
  7. NeurIPS 2024OneActor: Consistent Subject Generation via Cluster-Conditioned Guidance
  8. NeurIPS 2024Optimized Feature Generation for Tabular Data via LLMs with Decision Tree Reasoning
  9. NeurIPS 2024Order-Independence Without Fine Tuning
  10. NeurIPS 2024PhyloGen: Language Model-Enhanced Phylogenetic Inference via Graph Structure Generation
  11. NeurIPS 2024Predictive Attractor Models
  12. NeurIPS 2024Protecting Your LLMs with Information Bottleneck
  13. NeurIPS 2024PuLID: Pure and Lightning ID Customization via Contrastive Alignment
  14. NeurIPS 2024QuaRot: Outlier-Free 4-Bit Inference in Rotated LLMs
  15. NeurIPS 2024QVAE-Mole: The Quantum VAE with Spherical Latent Variable Learning for 3-D Molecule Generation
  16. NeurIPS 2024Rad-NeRF: Ray-decoupled Training of Neural Radiance Field
  17. NeurIPS 2024RankRAG: Unifying Context Ranking with Retrieval-Augmented Generation in LLMs
  18. NeurIPS 2024RectifID: Personalizing Rectified Flow with Anchored Classifier Guidance
  19. NeurIPS 2024RedCode: Risky Code Execution and Generation Benchmark for Code Agents
  20. NeurIPS 2024Reducing Transformer Key-Value Cache Size with Cross-Layer Attention
  21. NeurIPS 2024RepLiQA: A Question-Answering Dataset for Benchmarking LLMs on Unseen Reference Content
  22. NeurIPS 2024Reproducibility Study of "ITI-GEN: Inclusive Text-to-Image Generation"
  23. NeurIPS 2024Reranking Laws for Language Generation: A Communication-Theoretic Perspective
  24. NeurIPS 2024RL-GPT: Integrating Reinforcement Learning and Code-as-policy
  25. NeurIPS 2024SciCode: A Research Coding Benchmark Curated by Scientists
  26. NeurIPS 2024Score Distillation via Reparametrized DDIM
  27. NeurIPS 2024Score-based 3D molecule generation with neural fields
  28. NeurIPS 2024Selective Generation for Controllable Language Models
  29. NeurIPS 2024SelfCodeAlign: Self-Alignment for Code Generation
  30. NeurIPS 2024SemCoder: Training Code Language Models with Comprehensive Semantics Reasoning
  31. NeurIPS 2024SnapKV: LLM Knows What You are Looking for Before Generation
  32. NeurIPS 2024Source Code Foundation Models are Transferable Binary Analysis Knowledge Bases
  33. NeurIPS 2024SparseLLM: Towards Global Pruning of Pre-trained Language Models
  34. NeurIPS 2024Stable-Pose: Leveraging Transformers for Pose-Guided Text-to-Image Generation
  35. NeurIPS 2024Stylebreeder: Exploring and Democratizing Artistic Styles through Text-to-Image Models
  36. NeurIPS 2024Suppress Content Shift: Better Diffusion Features via Off-the-Shelf Generation Techniques
  37. NeurIPS 2024SWT-Bench: Testing and Validating Real-World Bug-Fixes with Code Agents
  38. NeurIPS 2024Synergistic Dual Spatial-aware Generation of Image-to-text and Text-to-image
  39. NeurIPS 2024Synthetic Programming Elicitation for Text-to-Code in Very Low-Resource Programming and Formal Languages
  40. NeurIPS 2024The ALCHEmist: Automated Labeling 500x CHEaper than LLM Data Annotators
  41. NeurIPS 2024Token Merging for Training-Free Semantic Binding in Text-to-Image Synthesis
  42. NeurIPS 2024Towards General Loop Invariant Generation: A Benchmark of Programs with Memory Manipulation
  43. NeurIPS 2024Trace is the Next AutoDiff: Generative Optimization with Rich Feedback, Execution Traces, and LLMs
  44. NeurIPS 2024U-DiTs: Downsample Tokens in U-Shaped Diffusion Transformers
  45. NeurIPS 2024UDA: A Benchmark Suite for Retrieval Augmented Generation in Real-World Document Analysis
  46. NeurIPS 2024UltraPixel: Advancing Ultra High-Resolution Image Synthesis to New Peaks
  47. NeurIPS 2024Unified Gradient-Based Machine Unlearning with Remain Geometry Enhancement
  48. NeurIPS 2024Verified Code Transpilation with LLMs
  49. NeurIPS 2024Web2Code: A Large-scale Webpage-to-Code Dataset and Evaluation Framework for Multimodal LLMs
  50. NeurIPS 2024Where does In-context Learning Happen in Large Language Models?

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