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 13 / 13 页

  1. NeurIPS 2025ShortListing Model: A Streamlined Simplex Diffusion for Discrete Variable Generation
  2. NeurIPS 2025SimpleStrat: Diversifying Language Model Generation with Stratification
  3. NeurIPS 2025SnapMoGen: Human Motion Generation from Expressive Texts
  4. NeurIPS 2025Sparse Image Synthesis via Joint Latent and RoI Flow
  5. NeurIPS 2025Sparse VideoGen2: Accelerate Video Generation with Sparse Attention via Semantic-Aware Permutation
  6. NeurIPS 2025SpecMER: Fast Protein Generation with K-mer Guided Speculative Decoding
  7. NeurIPS 2025Spotlight Attention: Towards Efficient LLM Generation via Non-linear Hashing-based KV Cache Retrieval
  8. NeurIPS 2025Steering When Necessary: Flexible Steering Large Language Models with Backtracking
  9. NeurIPS 2025Struct-Bench: A Benchmark for Differentially Private Structured Text Generation
  10. NeurIPS 2025SymRTLO: Enhancing RTL Code Optimization with LLMs and Neuron-Inspired Symbolic Reasoning
  11. NeurIPS 2025SynBrain: Enhancing Visual-to-fMRI Synthesis via Probabilistic Representation Learning
  12. NeurIPS 2025Synthesizing Performance Constraints for Evaluating and Improving Code Efficiency
  13. NeurIPS 2025Synthetic Series-Symbol Data Generation for Time Series Foundation Models
  14. NeurIPS 2025Table2LaTeX-RL: High-Fidelity LaTeX Code Generation from Table Images via Reinforced Multimodal Language Models
  15. NeurIPS 2025TEMPO: Temporal Multi-scale Autoregressive Generation of Protein Conformational Ensembles
  16. NeurIPS 2025Text-to-Code Generation for Modular Building Layouts in Building Information Modeling
  17. NeurIPS 2025The Automated LLM Speedrunning Benchmark: Reproducing NanoGPT Improvements
  18. NeurIPS 2025The Curse of Depth in Large Language Models
  19. NeurIPS 2025Top-H Decoding: Adapting the Creativity and Coherence with Bounded Entropy in Text Generation
  20. NeurIPS 2025Tortoise and Hare Guidance: Accelerating Diffusion Model Inference with Multirate Integration
  21. NeurIPS 2025Towards A Generalist Code Embedding Model Based On Massive Data Synthesis
  22. NeurIPS 2025Towards Better & Faster Autoregressive Image Generation: From the Perspective of Entropy
  23. NeurIPS 2025Towards Reliable Code-as-Policies: A Neuro-Symbolic Framework for Embodied Task Planning
  24. NeurIPS 2025Track, Inpaint, Resplat: Subject-driven 3D and 4D Generation with Progressive Texture Infilling
  25. NeurIPS 2025Training Language Models to Generate Quality Code with Program Analysis Feedback
  26. NeurIPS 2025Training-Free Constrained Generation With Stable Diffusion Models
  27. NeurIPS 2025Transforming Generic Coder LLMs to Effective Binary Code Embedding Models for Similarity Detection
  28. NeurIPS 2025TreeSynth: Synthesizing Diverse Data from Scratch via Tree-Guided Subspace Partitioning
  29. NeurIPS 2025Understanding and Mitigating Numerical Sources of Nondeterminism in LLM Inference
  30. NeurIPS 2025Understanding LLM Behaviors via Compression: Data Generation, Knowledge Acquisition and Scaling Laws
  31. NeurIPS 2025UniCTokens: Boosting Personalized Understanding and Generation via Unified Concept Tokens
  32. NeurIPS 2025Unified all-atom molecule generation with neural fields
  33. NeurIPS 2025Unlocking SLM Potential for Data Analysis Code Generation via Non-Parametric Knowledge Distillation
  34. NeurIPS 2025Vector Quantization in the Brain: Grid-like Codes in World Models
  35. NeurIPS 2025VeriLoC: Line-of-Code Level Prediction of Hardware Design Quality from Verilog Code
  36. NeurIPS 2025VeriThoughts: Enabling Automated Verilog Code Generation using Reasoning and Formal Verification
  37. NeurIPS 2025VETA-DiT: Variance-Equalized and Temporally Adaptive Quantization for Efficient 4-bit Diffusion Transformers
  38. NeurIPS 2025Vgent: Graph-based Retrieval-Reasoning-Augmented Generation For Long Video Understanding
  39. NeurIPS 2025vHector and HeisenVec: Scalable Vector Graphics Generation Through Large Language Models
  40. NeurIPS 2025VideoREPA: Learning Physics for Video Generation through Relational Alignment with Foundation Models
  41. NeurIPS 2025ViewCraft3D: High-fidelity and View-Consistent 3D Vector Graphics Synthesis
  42. NeurIPS 2025Wan-Move: Motion-controllable Video Generation via Latent Trajectory Guidance
  43. NeurIPS 2025WarpGAN: Warping-Guided 3D GAN Inversion with Style-Based Novel View Inpainting
  44. NeurIPS 2025WebGen-Bench: Evaluating LLMs on Generating Interactive and Functional Websites from Scratch
  45. NeurIPS 2025Win Fast or Lose Slow: Balancing Speed and Accuracy in Latency-Sensitive Decisions of LLMs

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