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 16 / 18 页

  1. NeurIPS 2026LLMs Optimizing LLMs: Automated MegaKernel Generation for Inference Acceleration
  2. NeurIPS 2026LLMs Show No Signs Of Individuated Metacognition
  3. NeurIPS 2026LoopNav: Benchmarking Spatial Consistency in World Models
  4. NeurIPS 2026LoopWeaver: Weaving Feedback Loops into Hierarchical Generation under Constraints
  5. NeurIPS 2026Machine Unlearning in Diffusion LLMs
  6. NeurIPS 2026Matchability-Aware Conformal Prediction for Open-Ended Language Model Generation
  7. NeurIPS 2026MDMR-Bench: A Multi-Dimensional Benchmark for Multi-Reference Image Generation
  8. NeurIPS 2026Measuring Layer-wise Intrinsic Dimensionality of FFNs in LLMs via PCA
  9. NeurIPS 2026MedIGen: Reliable Medical Illustration Generation via Interleaved Introspective Reasoning
  10. NeurIPS 2026Mesh BDF: Barycentric Dominance Field for 3D Native Mesh Generation
  11. NeurIPS 2026MetaLoop: Benchmarking the Full Metacognitive Loop in LLMs
  12. NeurIPS 2026MobTA: Bus-Conditioned Zero-Shot Trajectory Generation via Task Arithmetic
  13. NeurIPS 2026MoCA: Mixture-of-Components Attention for Scalable Compositional 3D Generation
  14. NeurIPS 2026MoCAR: Motion-code Coordinate-aware AutoRegression for Continuous Trajectory Forecasting
  15. NeurIPS 2026Motion Forcing: Decoupling Ego and Object Motion via Sparse Inputs for Structured Video Generation
  16. NeurIPS 2026N-vium: Mixture-of-Exits Transformer for Accelerated Exact Generation
  17. NeurIPS 2026Natural-Language-Guided Protein Generation for Ligand-Binding Design
  18. NeurIPS 2026NeuroSynTheos: Learning to accelerate counterexample-guided reactive synthesis modulo theories
  19. NeurIPS 2026NIV: Neural Axis Variations for Variable Font Generation
  20. NeurIPS 2026Norm Anchors Make Model Edits Last
  21. NeurIPS 2026On the Price of Privacy for Language Identification and Generation
  22. NeurIPS 2026On-Policy Distillation with Open Property-Equivalence Reward for LLM-Based NL-to-SVA Generation
  23. NeurIPS 2026One View Is Enough: In-the-Wild Monocular Pretraining for Novel View Generation
  24. NeurIPS 2026OopsWorld! Operation-Grounded Seamless World Generation
  25. NeurIPS 2026Orthrus: Memory-Efficient Parallel Token Generation via Dual-View Diffusion
  26. NeurIPS 2026OverLay++: Dense-Overlap Layout-to-Image Generation Dataset
  27. NeurIPS 2026P-EAGLE: Parallel-Drafting EAGLE with Scalable Training
  28. NeurIPS 2026P$^{3}$: Joint Program-and-Proof Planning\\ for Verified Code Generation
  29. NeurIPS 2026Panoptic Scene Program Diffusion Transformer
  30. NeurIPS 2026Parallel Rollout Approximation for Pixel-Space Autoregressive Image Generation
  31. NeurIPS 2026PBT-Bench: Benchmarking AI Agents on Property-Based Testing
  32. NeurIPS 2026Permit: Permission-Aware Representation Intervention for Controlled Generation in Large Language Models
  33. NeurIPS 2026Phase-wise MLLM Tuning for Multi-framework WebUI Code Generation
  34. NeurIPS 2026PhysAgentGym: Free Physical-Law Verifiers for Training Small Code-Reasoning Agents
  35. NeurIPS 2026Population-Aligned Persona Generation for LLM-based Social Simulation
  36. NeurIPS 2026Prefix Likelihood-Ratio Control: Tail-Stable Training for Long-Horizon Language Generation
  37. NeurIPS 2026Primal Generation, Dual Judgment: Self-Training from Test-Time Scaling
  38. NeurIPS 2026Primal-Dual Flow Matching for Sample-Wise Constrained Generation
  39. NeurIPS 2026PRO: Enabling Precise and Robust Text Watermark for Open-Source LLMs
  40. NeurIPS 2026Property-Guided LLM Program Synthesis for Planning
  41. NeurIPS 2026PSD: Pushing the Pareto Frontier of Diffusion LLMs via Parallel Speculative Decoding
  42. NeurIPS 2026RAVEL: Rare Concept Generation and Editing via Graph-driven Relational Guidance
  43. NeurIPS 2026Re-evaluating Confidence Remasking in Masked Diffusion Language Models
  44. NeurIPS 2026Recursive Language Models
  45. NeurIPS 2026Refactoring Code Through Library Design
  46. NeurIPS 2026REFLEX: RNA Ensemble Generation via Flexibility-Calibrated Stochastic Bridge
  47. NeurIPS 2026Reinforcement Learning for Code Optimization
  48. NeurIPS 2026Reinforcement Learning with Verifiable Physics: Post-training LLMs for PDE Solver Generation
  49. NeurIPS 2026Render Structure Uncertainty for HTML Repair in MLLM-based UI-to-Code Generation
  50. NeurIPS 2026RepoZero: Can LLMs Generate a Code Repository from Scratch?

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