代码生成论文趋势 2023–2026

主要结论

• 代码生成论文从 2023 年的 210 篇增长到 2026 年的 860 篇，三年间扩大到约 4.1 倍。
• NeurIPS 是发代码生成论文最多的会议，2023–2026 年共 630 篇，占四个会议总量的 29%。
• 交叉方向里涨得最快的是AI 智能体：同时属于两个主题的论文从 2023 年的 0 篇增至 2026 年的 93 篇。
• 在「自然语言」的 5 个主题里，它的 2026 年论文数排第 1；同组增长最快的检索增强生成是 5.4 倍，代码生成是 4.1 倍。

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

• NeurIPS 2026A Theoretical Analysis of Test-Driven Code Generation
• ICML 2026$A_2$DEPT: Large Language Model–Driven Automated Algorithm Design via Evolutionary Program Trees
• ICLR 2026A Bayesian Nonparametric Framework for Private, Fair, and Balanced Tabular Data Synthesis
• CVPR 2026ACPV-Net All-Class Polygonal Vectorization for Seamless Vector Map Generation from
• NeurIPS 2025$\texttt{STRCMP}$: Integrating Graph Structural Priors with Language Models for Combinatorial Optimization
• ICML 2025AlphaVerus: Bootstrapping Formally Verified Code Generation through Self-Improving Translation and Treefinement
• ICLR 2025Automated Proof Generation for Rust Code via Self-Evolution
• CVPR 2025ArtFormer: Controllable Generation of Diverse 3D Articulated Objects
• NeurIPS 2024AMBROSIA: A Benchmark for Parsing Ambiguous Questions into Database Queries
• ICML 2024ACM-MILP: Adaptive Constraint Modification via Grouping and Selection for Hardness-Preserving MILP Instance Generation
• ICLR 2024CODE REPRESENTATION LEARNING AT SCALE
• CVPR 2024Desigen: A Pipeline for Controllable Design Template Generation
• NeurIPS 2023ANPL: Towards Natural Programming with Interactive Decomposition
• ICML 2023Can Large Language Models Reason about Program Invariants?
• ICLR 2023Binding Language Models in Symbolic Languages
• CVPR 2023Attribute-Preserving Face Dataset Anonymization via Latent Code Optimization
• NeurIPS 2026A Theory of Time-Sensitive Language Generation: Sparse Hallucination Beats Mode Collapse
• ICML 2026Beyond Problem Solving: UOJ-Bench for Evaluating Code Generation, Hacking, and Repair in Competitive Programming
• ICLR 2026AssetFormer: Modular 3D Assets Generation with Autoregressive Transformer
• CVPR 2026Animator-Centric Skeleton Generation on Objects with Fine-Grained Details

全部代码生成论文

共 446 篇，第 1 / 9 页

1. CVPR 20243D Feature Tracking via Event Camera
2. CVPR 2024A Recipe for Scaling up Text-to-Video Generation with Text-free Videos
3. CVPR 2024A Unified and Interpretable Emotion Representation and Expression Generation
4. CVPR 2024Activity-Biometrics: Person Identification from Daily Activities
5. CVPR 2024Adversarial Text to Continuous Image Generation
6. CVPR 2024Arbitrary-Scale Image Generation and Upsampling using Latent Diffusion Model and Implicit Neural Decoder
7. CVPR 2024AttriHuman-3D: Editable 3D Human Avatar Generation with Attribute Decomposition and Indexing
8. CVPR 2024AvatarGPT: All-in-One Framework for Motion Understanding Planning Generation and Beyond
9. CVPR 2024BerfScene: Bev-conditioned Equivariant Radiance Fields for Infinite 3D Scene Generation
10. CVPR 2024BiPer: Binary Neural Networks using a Periodic Function
11. CVPR 2024Boosting Adversarial Training via Fisher-Rao Norm-based Regularization
12. CVPR 2024BrainWash: A Poisoning Attack to Forget in Continual Learning
13. CVPR 2024CAD: Photorealistic 3D Generation via Adversarial Distillation
14. CVPR 2024CAGE: Controllable Articulation GEneration
15. CVPR 2024CapHuman: Capture Your Moments in Parallel Universes
16. CVPR 2024Causal-CoG: A Causal-Effect Look at Context Generation for Boosting Multi-modal Language Models
17. CVPR 2024ChatScene: Knowledge-Enabled Safety-Critical Scenario Generation for Autonomous Vehicles
18. CVPR 2024Clockwork Diffusion: Efficient Generation With Model-Step Distillation
19. CVPR 2024Coarse-to-Fine Latent Diffusion for Pose-Guided Person Image Synthesis
20. CVPR 2024CoDe: An Explicit Content Decoupling Framework for Image Restoration
21. CVPR 2024CoDi: Conditional Diffusion Distillation for Higher-Fidelity and Faster Image Generation
22. CVPR 2024Condition-Aware Neural Network for Controlled Image Generation
23. CVPR 2024Constrained Layout Generation with Factor Graphs
24. CVPR 2024ControlRoom3D: Room Generation using Semantic Proxy Rooms
25. CVPR 2024Correcting Diffusion Generation through Resampling
26. CVPR 2024DanceCamera3D: 3D Camera Movement Synthesis with Music and Dance
27. CVPR 2024DemoCaricature: Democratising Caricature Generation with a Rough Sketch
28. CVPR 2024DemoFusion: Democratising High-Resolution Image Generation With No $$$
29. CVPR 2024Desigen: A Pipeline for Controllable Design Template Generation
30. CVPR 2024Design2Cloth: 3D Cloth Generation from 2D Masks
31. CVPR 2024DiffInDScene: Diffusion-based High-Quality 3D Indoor Scene Generation
32. CVPR 2024Diffusion Time-step Curriculum for One Image to 3D Generation
33. CVPR 2024DisCo: Disentangled Control for Realistic Human Dance Generation
34. CVPR 2024Discriminative Probing and Tuning for Text-to-Image Generation
35. CVPR 2024DreamComposer: Controllable 3D Object Generation via Multi-View Conditions
36. CVPR 2024DreamSalon: A Staged Diffusion Framework for Preserving Identity-Context in Editable Face Generation
37. CVPR 2024DSGG: Dense Relation Transformer for an End-to-end Scene Graph Generation
38. CVPR 2024EGTR: Extracting Graph from Transformer for Scene Graph Generation
39. CVPR 2024ElasticDiffusion: Training-free Arbitrary Size Image Generation through Global-Local Content Separation
40. CVPR 2024Emu Edit: Precise Image Editing via Recognition and Generation Tasks
41. CVPR 2024FaceChain-SuDe: Building Derived Class to Inherit Category Attributes for One-shot Subject-Driven Generation
42. CVPR 2024FlowDiffuser: Advancing Optical Flow Estimation with Diffusion Models
43. CVPR 2024FlowVQTalker: High-Quality Emotional Talking Face Generation through Normalizing Flow and Quantization
44. CVPR 2024FreeCustom: Tuning-Free Customized Image Generation for Multi-Concept Composition
45. CVPR 2024FreeU: Free Lunch in Diffusion U-Net
46. CVPR 2024From Correspondences to Pose: Non-minimal Certifiably Optimal Relative Pose without Disambiguation
47. CVPR 2024Gaussian Shell Maps for Efficient 3D Human Generation
48. CVPR 2024Generalizable Face Landmarking Guided by Conditional Face Warping
49. CVPR 2024Generate Like Experts: Multi-Stage Font Generation by Incorporating Font Transfer Process into Diffusion Models
50. CVPR 2024Generating Illustrated Instructions

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。