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 7 / 13 页

  1. NeurIPS 2025Efficient Pre-Training of LLMs via Topology-Aware Communication Alignment on More Than 9600 GPUs
  2. NeurIPS 2025Efficient semantic uncertainty quantification in language models via diversity-steered sampling
  3. NeurIPS 2025EnzyControl: Adding Functional and Substrate-Specific Control for Enzyme Backbone Generation
  4. NeurIPS 2025ESCA: Contextualizing Embodied Agents via Scene-Graph Generation
  5. NeurIPS 2025EVAAA: A Virtual Environment Platform for Essential Variables in Autonomous and Adaptive Agents
  6. NeurIPS 2025EVODiff: Entropy-aware Variance Optimized Diffusion Inference
  7. NeurIPS 2025Execution Guided Line-by-Line Code Generation
  8. NeurIPS 2025FACT: Mitigating Inconsistent Hallucinations in LLMs via Fact-Driven Alternating Code-Text Training
  9. NeurIPS 2025Failure by Interference: Language Models Make Balanced Parentheses Errors When Faulty Mechanisms Overshadow Sound Ones
  10. NeurIPS 2025FAST: Foreground‑aware Diffusion with Accelerated Sampling Trajectory for Segmentation‑oriented Anomaly Synthesis
  11. NeurIPS 2025Feedback Guidance of Diffusion Models
  12. NeurIPS 2025FlashMo: Geometric Interpolants and Frequency-Aware Sparsity for Scalable Efficient Motion Generation
  13. NeurIPS 2025Flatten Graphs as Sequences: Transformers are Scalable Graph Generators
  14. NeurIPS 2025Flexible MOF Generation with Torsion-Aware Flow Matching
  15. NeurIPS 2025FlexWorld: Progressively Expanding 3D Scenes for Flexible-View Exploration
  16. NeurIPS 2025Force Prompting: Video Generation Models Can Learn And Generalize Physics-based Control Signals
  17. NeurIPS 2025Forging Time Series with Language: A Large Language Model Approach to Synthetic Data Generation
  18. NeurIPS 2025Fourier Token Merging: Understanding and Capitalizing Frequency Domain for Efficient Image Generation
  19. NeurIPS 2025Free-Lunch Color-Texture Disentanglement for Stylized Image Generation
  20. NeurIPS 2025FreqPolicy: Frequency Autoregressive Visuomotor Policy with Continuous Tokens
  21. NeurIPS 2025From Programs to Poses: Factored Real-World Scene Generation via Learned Program Libraries
  22. NeurIPS 2025FuncGenFoil: Airfoil Generation and Editing Model in Function Space
  23. NeurIPS 2025Fused View-Time Attention and Feedforward Reconstruction for 4D Scene Generation
  24. NeurIPS 2025Generating Computational Cognitive models using Large Language Models
  25. NeurIPS 2025GeoCAD: Local Geometry-Controllable CAD Generation with Large Language Models
  26. NeurIPS 2025GPSToken: Gaussian Parameterized Spatially-adaptive Tokenization for Image Representation and Generation
  27. NeurIPS 2025Greed is Good: A Unifying Perspective on Guided Generation
  28. NeurIPS 2025HairFree: Compositional 2D Head Prior for Text-Driven 360° Bald Texture Synthesis
  29. NeurIPS 2025Hawk: Leveraging Spatial Context for Faster Autoregressive Text-to-Image Generation
  30. NeurIPS 2025HBLLM: Wavelet-Enhanced High-Fidelity 1-Bit Quantization for LLMs
  31. NeurIPS 2025Hierarchical Koopman Diffusion: Fast Generation with Interpretable Diffusion Trajectory
  32. NeurIPS 2025HiFlow: Training-free High-Resolution Image Generation with Flow-Aligned Guidance
  33. NeurIPS 2025Hogwild! Inference: Parallel LLM Generation via Concurrent Attention
  34. NeurIPS 2025HyPlaneHead: Rethinking Tri-plane-like Representations in Full-Head Image Synthesis
  35. NeurIPS 2025Improving Regret Approximation for Unsupervised Dynamic Environment Generation
  36. NeurIPS 2025Improving the Euclidean Diffusion Generation of Manifold Data by Mitigating Score Function Singularity
  37. NeurIPS 2025Inference-Time Scaling for Flow Models via Stochastic Generation and Rollover Budget Forcing
  38. NeurIPS 2025Influence Guided Context Selection for Effective Retrieval-Augmented Generation
  39. NeurIPS 2025InstanceAssemble: Layout-Aware Image Generation via Instance Assembling Attention
  40. NeurIPS 2025InstructFlow: Adaptive Symbolic Constraint-Guided Code Generation for Long-Horizon Planning
  41. NeurIPS 2025IntrinsiX: High-Quality PBR Generation using Image Priors
  42. NeurIPS 2025Joint Relational Database Generation via Graph-Conditional Diffusion Models
  43. NeurIPS 2025Keep It on a Leash: Controllable Pseudo-label Generation Towards Realistic Long-Tailed Semi-Supervised Learning
  44. NeurIPS 2025KVLink: Accelerating Large Language Models via Efficient KV Cache Reuse
  45. NeurIPS 2025KVzip: Query-Agnostic KV Cache Compression with Context Reconstruction
  46. NeurIPS 2025Large Language Diffusion Models
  47. NeurIPS 2025Lessons Learned: A Multi-Agent Framework for Code LLMs to Learn and Improve
  48. NeurIPS 2025Let's Revise Step-by-Step: A Unified Local Search Framework for Code Generation with LLMs
  49. NeurIPS 2025LeVo: High-Quality Song Generation with Multi-Preference Alignment
  50. NeurIPS 2025Limited Preference Data? Learning Better Reward Model with Latent Space Synthesis

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