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 645 篇，第 5 / 13 页

  1. ICLR 2025ControlAR: Controllable Image Generation with Autoregressive Models
  2. ICLR 2025Controllable Generation via Locally Constrained Resampling
  3. ICLR 2025ConvCodeWorld: Benchmarking Conversational Code Generation in Reproducible Feedback Environments
  4. ICLR 2025Copyright-Protected Language Generation via Adaptive Model Fusion
  5. ICLR 2025CoRNStack: High-Quality Contrastive Data for Better Code Retrieval and Reranking
  6. ICLR 2025Correlation and Navigation in the Vocabulary Key Representation Space of Language Models
  7. ICLR 2025CraftRTL: High-quality Synthetic Data Generation for Verilog Code Models with Correct-by-Construction Non-Textual Representations and Targeted Code Repair
  8. ICLR 2025CubeDiff: Repurposing Diffusion-Based Image Models for Panorama Generation
  9. ICLR 2025DataGen: Unified Synthetic Dataset Generation via Large Language Models
  10. ICLR 2025DAWN: Dynamic Frame Avatar with Non-autoregressive Diffusion Framework for Talking head Video Generation
  11. ICLR 2025DeepRTL: Bridging Verilog Understanding and Generation with a Unified Representation Model
  12. ICLR 2025Diffusing to the Top: Boost Graph Neural Networks with Minimal Hyperparameter Tuning
  13. ICLR 2025Diffusion On Syntax Trees For Program Synthesis
  14. ICLR 2025Diffusion-based Neural Network Weights Generation
  15. ICLR 2025DiscoveryBench: Towards Data-Driven Discovery with Large Language Models
  16. ICLR 2025Discrete Distribution Networks
  17. ICLR 2025Drop-Upcycling: Training Sparse Mixture of Experts with Partial Re-initialization
  18. ICLR 2025DynamicCity: Large-Scale 4D Occupancy Generation from Dynamic Scenes
  19. ICLR 2025ECHOPulse: ECG Controlled Echocardio-gram Video Generation
  20. ICLR 2025Emerging Safety Attack and Defense in Federated Instruction Tuning of Large Language Models
  21. ICLR 2025ESE: Espresso Sentence Embeddings
  22. ICLR 2025Execution-guided within-prompt search for programming-by-example
  23. ICLR 2025Explore Theory of Mind: program-guided adversarial data generation for theory of mind reasoning
  24. ICLR 2025FaithEval: Can Your Language Model Stay Faithful to Context, Even If "The Moon is Made of Marshmallows"
  25. ICLR 2025Fast Direct: Query-Efficient Online Black-box Guidance for Diffusion-model Target Generation
  26. ICLR 2025FlexCAD: Unified and Versatile Controllable CAD Generation with Fine-tuned Large Language Models
  27. ICLR 2025Forking Paths in Neural Text Generation
  28. ICLR 2025FreCaS: Efficient Higher-Resolution Image Generation via Frequency-aware Cascaded Sampling
  29. ICLR 2025FreeVS: Generative View Synthesis on Free Driving Trajectory
  30. ICLR 2025From Few to Many: Self-Improving Many-Shot Reasoners Through Iterative Optimization and Generation
  31. ICLR 2025GALA: Geometry-Aware Local Adaptive Grids for Detailed 3D Generation
  32. ICLR 2025Generating CAD Code with Vision-Language Models for 3D Designs
  33. ICLR 2025GeSubNet: Gene Interaction Inference for Disease Subtype Network Generation
  34. ICLR 2025GOLD: Graph Out-of-Distribution Detection via Implicit Adversarial Latent Generation
  35. ICLR 2025Guaranteed Generation from Large Language Models
  36. ICLR 2025Gumbel Counterfactual Generation From Language Models
  37. ICLR 2025How efficient is LLM-generated code? A rigorous & high-standard benchmark
  38. ICLR 2025HyperPLR: Hypergraph Generation through Projection, Learning, and Reconstruction
  39. ICLR 2025HyPoGen: Optimization-Biased Hypernetworks for Generalizable Policy Generation
  40. ICLR 2025Improving Uncertainty Estimation through Semantically Diverse Language Generation
  41. ICLR 2025InCoDe: Interpretable Compressed Descriptions For Image Generation
  42. ICLR 2025Innovative Thinking, Infinite Humor: Humor Research of Large Language Models through Structured Thought Leaps
  43. ICLR 2025InsightBench: Evaluating Business Analytics Agents Through Multi-Step Insight Generation
  44. ICLR 2025InstructRAG: Instructing Retrieval-Augmented Generation via Self-Synthesized Rationales
  45. ICLR 2025IRIS: LLM-Assisted Static Analysis for Detecting Security Vulnerabilities
  46. ICLR 2025Is Factuality Enhancement a Free Lunch For LLMs? Better Factuality Can Lead to Worse Context-Faithfulness
  47. ICLR 2025It Helps to Take a Second Opinion: Teaching Smaller LLMs To Deliberate Mutually via Selective Rationale Optimisation
  48. ICLR 2025IterGen: Iterative Semantic-aware Structured LLM Generation with Backtracking
  49. ICLR 2025Large Language Models are Interpretable Learners
  50. ICLR 2025LayerDAG: A Layerwise Autoregressive Diffusion Model for Directed Acyclic Graph 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