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 6 / 18 页

  1. ICLR 2026Code Driven Planning with Domain-Adaptive Selector
  2. ICLR 2026Code World Models for General Game Playing
  3. ICLR 2026CodeGenGuard: A Robust Watermark for Code Generation Models
  4. ICLR 2026CodeSense: a Real-World Benchmark and Dataset for Code Semantic Reasoning
  5. ICLR 2026COLD-Steer: Steering Large Language Models via In-Context One-step Learning Dynamics
  6. ICLR 2026Condition Errors Refinement in Autoregressive Image Generation with Diffusion Loss
  7. ICLR 2026Constrained Decoding of Diffusion LLMs with Context-Free Grammars
  8. ICLR 2026Continuously Augmented Discrete Diffusion model for Categorical Generative Modeling
  9. ICLR 2026Critic–Adviser–Reviser Cyclic Refinement: Towards High-Quality EMR Corpus Generation with LLMs
  10. ICLR 2026Cross-ControlNet: Training-Free Fusion of Multiple Conditions for Text-to-Image Generation
  11. ICLR 2026CrossPL: Systematic Evaluation of Large Language Models for Cross Programming Language Interoperating Code Generation
  12. ICLR 2026CTBench: Cryptocurrency Time Series Generation Benchmark
  13. ICLR 2026DAComp: Benchmarking Data Agents across the Full Data Intelligence Lifecycle
  14. ICLR 2026Data Provenance for Image Auto-Regressive Generation
  15. ICLR 2026DCFold: Efficient Protein Structure Generation with Single Forward Pass
  16. ICLR 2026DeepRAG: Thinking to Retrieve Step by Step for Large Language Models
  17. ICLR 2026DELTA-Code: How RL Unlocks and Transfers New Programming Algorithms in LLMs
  18. ICLR 2026DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation
  19. ICLR 2026Diffusion Language Model Knows the Answer Before It Decodes
  20. ICLR 2026Diffusion LLMs Can Do Faster-Than-AR Inference via Discrete Diffusion Forcing
  21. ICLR 2026Directional Textual Inversion for Personalized Text-to-Image Generation
  22. ICLR 2026Disentangled Hierarchical VAE for 3D Human-Human Interaction Generation
  23. ICLR 2026DistillKac: Few-Step Image Generation via Damped Wave Equations
  24. ICLR 2026Do LLMs Forget What They Should? Evaluating In-Context Forgetting in Large Language Models
  25. ICLR 2026Don't Throw Away Your Pretrained Model
  26. ICLR 2026DreamOn: Diffusion Language Models For Code Infilling Beyond Fixed-size Canvas
  27. ICLR 2026EasyTune: Efficient Step-Aware Fine-Tuning for Diffusion-Based Motion Generation
  28. ICLR 2026ELLMob: Event-Driven Human Mobility Generation with Self-Aligned LLM Framework
  29. ICLR 2026Energy-Efficient Random Variate Generation via Compressed Lookup Tables
  30. ICLR 2026Enhancing Instruction Following of LLMs via Activation Steering with Dynamic Rejection
  31. ICLR 2026Enhancing Trustworthiness of Fine-Tuned LLMs via Regularized Subset Selection
  32. ICLR 2026Equilibrium Language Models
  33. ICLR 2026Event-T2M: Event-level Conditioning for Complex Text-to-Motion Synthesis
  34. ICLR 2026Evolving Graph Structured Programs for Circuit Generation with Large Language Models
  35. ICLR 2026ExpertLongBench: Benchmarking Language Models on Expert-Level Long-Form Generation Tasks with Structured Checklists
  36. ICLR 2026Exploring Diverse Generation Paths via Inference-time Stiefel Activation Steering
  37. ICLR 2026FACM: Flow-Anchored Consistency Models
  38. ICLR 2026FHE-Coder: Secure Agentic Code Generation for Fully Homomorphic Encryption
  39. ICLR 2026Figma2Code: Automating Multimodal Design to Code in the Wild
  40. ICLR 2026Flow Caching for Autoregressive Video Generation
  41. ICLR 2026From Large to Small: Transferring CUDA Optimization Expertise via Reasoning Graph
  42. ICLR 2026From Prediction to Perfection: Introducing Refinement to Autoregressive Image Generation
  43. ICLR 2026From Reproduction to Replication: Evaluating Research Agents with Progressive Code Masking
  44. ICLR 2026From Verifiable Dot to Reward Chain: Harnessing Verifiable Reference-based Rewards for Reinforcement Learning of Open-ended Generation
  45. ICLR 2026FullPart: Generating each 3D Part at Full Resolution
  46. ICLR 2026FutureFill: Fast Generation from Convolutional Sequence Models
  47. ICLR 2026GarmentGPT: Compositional Garment Pattern Generation via Discrete Latent Tokenization
  48. ICLR 2026Generalizable Heuristic Generation Through LLMs with Meta-Optimization
  49. ICLR 2026Generate Any Scene: Scene Graph Driven Data Synthesis for Visual Generation Training
  50. ICLR 2026Generation then Reconstruction: Accelerating Masked Autoregressive Models via Two-Stage Sampling

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