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 8 / 9 页

  1. NeurIPS 2024EffiBench: Benchmarking the Efficiency of Automatically Generated Code
  2. NeurIPS 2024EffiLearner: Enhancing Efficiency of Generated Code via Self-Optimization
  3. NeurIPS 2024EgoSim: An Egocentric Multi-view Simulator and Real Dataset for Body-worn Cameras during Motion and Activity
  4. NeurIPS 2024Einsum Benchmark: Enabling the Development of Next-Generation Tensor Execution Engines
  5. NeurIPS 2024ENAT: Rethinking Spatial-temporal Interactions in Token-based Image Synthesis
  6. NeurIPS 2024Equivariant Neural Diffusion for Molecule Generation
  7. NeurIPS 2024Era3D: High-Resolution Multiview Diffusion using Efficient Row-wise Attention
  8. NeurIPS 2024Erasing Undesirable Concepts in Diffusion Models with Adversarial Preservation
  9. NeurIPS 2024EvoCodeBench: An Evolving Code Generation Benchmark with Domain-Specific Evaluations
  10. NeurIPS 2024Exploring DCN-like architecture for fast image generation with arbitrary resolution
  11. NeurIPS 2024Face2QR: A Unified Framework for Aesthetic, Face-Preserving, and Scannable QR Code Generation
  12. NeurIPS 2024FlowTurbo: Towards Real-time Flow-Based Image Generation with Velocity Refiner
  13. NeurIPS 2024From Instance Training to Instruction Learning: Task Adapters Generation from Instructions
  14. NeurIPS 2024FuseAnyPart: Diffusion-Driven Facial Parts Swapping via Multiple Reference Images
  15. NeurIPS 2024GAVEL: Generating Games via Evolution and Language Models
  16. NeurIPS 2024Gorilla: Large Language Model Connected with Massive APIs
  17. NeurIPS 2024Grammar-Aligned Decoding
  18. NeurIPS 2024Grasp as You Say: Language-guided Dexterous Grasp Generation
  19. NeurIPS 2024Guided Trajectory Generation with Diffusion Models for Offline Model-based Optimization
  20. NeurIPS 2024Guiding a Diffusion Model with a Bad Version of Itself
  21. NeurIPS 2024HARMONIC: Harnessing LLMs for Tabular Data Synthesis and Privacy Protection
  22. NeurIPS 2024Hierarchical Programmatic Option Framework
  23. NeurIPS 2024Hints-In-Browser: Benchmarking Language Models for Programming Feedback Generation
  24. NeurIPS 2024HumanVid: Demystifying Training Data for Camera-controllable Human Image Animation
  25. NeurIPS 2024Hypothesis Testing the Circuit Hypothesis in LLMs
  26. NeurIPS 2024IaC-Eval: A Code Generation Benchmark for Cloud Infrastructure-as-Code Programs
  27. NeurIPS 2024IDGen: Item Discrimination Induced Prompt Generation for LLM Evaluation
  28. NeurIPS 2024IF-Font: Ideographic Description Sequence-Following Font Generation
  29. NeurIPS 2024Image Understanding Makes for A Good Tokenizer for Image Generation
  30. NeurIPS 2024IMAGPose: A Unified Conditional Framework for Pose-Guided Person Generation
  31. NeurIPS 2024Improved Distribution Matching Distillation for Fast Image Synthesis
  32. NeurIPS 2024Improved Generation of Adversarial Examples Against Safety-aligned LLMs
  33. NeurIPS 2024INDICT: Code Generation with Internal Dialogues of Critiques for Both Security and Helpfulness
  34. NeurIPS 2024InfiBench: Evaluating the Question-Answering Capabilities of Code Large Language Models
  35. NeurIPS 2024IntraMix: Intra-Class Mixup Generation for Accurate Labels and Neighbors
  36. NeurIPS 2024IRCAN: Mitigating Knowledge Conflicts in LLM Generation via Identifying and Reweighting Context-Aware Neurons
  37. NeurIPS 2024Is Programming by Example Solved by LLMs?
  38. NeurIPS 2024kGym: A Platform and Dataset to Benchmark Large Language Models on Linux Kernel Crash Resolution
  39. NeurIPS 2024Language Generation in the Limit
  40. NeurIPS 2024Language Without Borders: A Dataset and Benchmark for Code-Switching Lip Reading
  41. NeurIPS 2024Language-Driven Interactive Traffic Trajectory Generation
  42. NeurIPS 2024Learning to Reason via Program Generation, Emulation, and Search
  43. NeurIPS 2024LeDex: Training LLMs to Better Self-Debug and Explain Code
  44. NeurIPS 2024LLMDFA: Analyzing Dataflow in Code with Large Language Models
  45. NeurIPS 2024Mercury: A Code Efficiency Benchmark for Code Large Language Models
  46. NeurIPS 2024MILP-StuDio: MILP Instance Generation via Block Structure Decomposition
  47. NeurIPS 2024MSA Generation with Seqs2Seqs Pretraining: Advancing Protein Structure Predictions
  48. NeurIPS 2024Natural Counterfactuals With Necessary Backtracking
  49. NeurIPS 2024Nearest Neighbor Speculative Decoding for LLM Generation and Attribution
  50. NeurIPS 2024Neural Residual Diffusion Models for Deep Scalable Vision 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