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 446 篇，第 9 / 9 页

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

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