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 10 / 13 页

  1. NeurIPS 2025CodeGEMM: A Codebook-Centric Approach to Efficient GEMM in Quantized LLMs
  2. NeurIPS 2025Color Conditional Generation with Sliced Wasserstein Guidance
  3. NeurIPS 2025COME: Adding Scene-Centric Forecasting Control to Occupancy World Model
  4. NeurIPS 2025Compositional Discrete Latent Code for High Fidelity, Productive Diffusion Models
  5. NeurIPS 2025Consistent Story Generation: Unlocking the Potential of Zigzag Sampling
  6. NeurIPS 2025Constrained Discrete Diffusion
  7. NeurIPS 2025Contact Map Transfer with Conditional Diffusion Model for Generalizable Dexterous Grasp Generation
  8. NeurIPS 2025Contextual Thompson Sampling via Generation of Missing Data
  9. NeurIPS 2025Cooperative Retrieval-Augmented Generation for Question Answering: Mutual Information Exchange and Ranking by Contrasting Layers
  10. NeurIPS 2025CoRe: Benchmarking LLMs’ Code Reasoning Capabilities through Static Analysis Tasks
  11. NeurIPS 2025CORE: Reducing UI Exposure in Mobile Agents via Collaboration Between Cloud and Local LLMs
  12. NeurIPS 2025CoT-lized Diffusion: Let's Reinforce T2I Generation Step-by-step
  13. NeurIPS 2025CSGO: Content-Style Composition in Text-to-Image Generation
  14. NeurIPS 2025Cue3D: Quantifying the Role of Image Cues in Single-Image 3D Generation
  15. NeurIPS 2025CURE: Co-Evolving Coders and Unit Testers via Reinforcement Learning
  16. NeurIPS 2025CymbaDiff: Structured Spatial Diffusion for Sketch-based 3D Semantic Urban Scene Generation
  17. NeurIPS 2025DeltaFormer: Unlock the state space of Transformer
  18. NeurIPS 2025Diffusion Beats Autoregressive in Data-Constrained Settings
  19. NeurIPS 2025DINGO: Constrained Inference for Diffusion LLMs
  20. NeurIPS 2025Direct Numerical Layout Generation for 3D Indoor Scene Synthesis via Spatial Reasoning
  21. NeurIPS 2025Direct3D-S2: Gigascale 3D Generation Made Easy with Spatial Sparse Attention
  22. NeurIPS 2025Discovering Latent Graphs with GFlowNets for Diverse Conditional Image Generation
  23. NeurIPS 2025Distilled Decoding 2: One-step Sampling of Image Auto-regressive Models with Conditional Score Distillation
  24. NeurIPS 2025Distilling LLM Agent into Small Models with Retrieval and Code Tools
  25. NeurIPS 2025DMol: A Highly Efficient and Chemical Motif-Preserving Molecule Generation Platform
  26. NeurIPS 2025Document Summarization with Conformal Importance Guarantees
  27. NeurIPS 2025DoDo-Code: an Efficient Levenshtein Distance Embedding-based Code for 4-ary IDS Channel
  28. NeurIPS 2025DyFlow: Dynamic Workflow Framework for Agentic Reasoning
  29. NeurIPS 2025EffiBench-X: A Multi-Language Benchmark for Measuring Efficiency of LLM-Generated Code
  30. NeurIPS 2025Efficient Pre-Training of LLMs via Topology-Aware Communication Alignment on More Than 9600 GPUs
  31. NeurIPS 2025Efficient semantic uncertainty quantification in language models via diversity-steered sampling
  32. NeurIPS 2025EnzyControl: Adding Functional and Substrate-Specific Control for Enzyme Backbone Generation
  33. NeurIPS 2025ESCA: Contextualizing Embodied Agents via Scene-Graph Generation
  34. NeurIPS 2025EVAAA: A Virtual Environment Platform for Essential Variables in Autonomous and Adaptive Agents
  35. NeurIPS 2025EVODiff: Entropy-aware Variance Optimized Diffusion Inference
  36. NeurIPS 2025Execution Guided Line-by-Line Code Generation
  37. NeurIPS 2025FACT: Mitigating Inconsistent Hallucinations in LLMs via Fact-Driven Alternating Code-Text Training
  38. NeurIPS 2025Failure by Interference: Language Models Make Balanced Parentheses Errors When Faulty Mechanisms Overshadow Sound Ones
  39. NeurIPS 2025FAST: Foreground‑aware Diffusion with Accelerated Sampling Trajectory for Segmentation‑oriented Anomaly Synthesis
  40. NeurIPS 2025Feedback Guidance of Diffusion Models
  41. NeurIPS 2025FlashMo: Geometric Interpolants and Frequency-Aware Sparsity for Scalable Efficient Motion Generation
  42. NeurIPS 2025Flatten Graphs as Sequences: Transformers are Scalable Graph Generators
  43. NeurIPS 2025Flexible MOF Generation with Torsion-Aware Flow Matching
  44. NeurIPS 2025FlexWorld: Progressively Expanding 3D Scenes for Flexible-View Exploration
  45. NeurIPS 2025Force Prompting: Video Generation Models Can Learn And Generalize Physics-based Control Signals
  46. NeurIPS 2025Forging Time Series with Language: A Large Language Model Approach to Synthetic Data Generation
  47. NeurIPS 2025Fourier Token Merging: Understanding and Capitalizing Frequency Domain for Efficient Image Generation
  48. NeurIPS 2025Free-Lunch Color-Texture Disentanglement for Stylized Image Generation
  49. NeurIPS 2025FreqPolicy: Frequency Autoregressive Visuomotor Policy with Continuous Tokens
  50. NeurIPS 2025From Programs to Poses: Factored Real-World Scene Generation via Learned Program Libraries

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