Code Generation papers, 2023–2026

Key findings

• Code Generation went from 210 papers in 2023 to 860 in 2026, roughly 4.1x in three years.
• NeurIPS publishes the most Code Generation work: 630 papers from 2023 to 2026, 29% of the four-venue total.
• The fastest-growing overlap is with AI Agents: papers tagged with both rose from 0 in 2023 to 93 in 2026.
• Among the 5 topics under Natural Language, it ranks #1 by 2026 paper count; the fastest grower in the group, Retrieval-Augmented Generation, is up 5.4x versus 4.1x here.

Representative papers

Spread across years and venues so every edition shows up

• 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

All Code Generation papers

135 papers, page 2 of 3

51. NeurIPS 2024FlowTurbo: Towards Real-time Flow-Based Image Generation with Velocity Refiner
52. NeurIPS 2024From Instance Training to Instruction Learning: Task Adapters Generation from Instructions
53. NeurIPS 2024FuseAnyPart: Diffusion-Driven Facial Parts Swapping via Multiple Reference Images
54. NeurIPS 2024GAVEL: Generating Games via Evolution and Language Models
55. NeurIPS 2024Gorilla: Large Language Model Connected with Massive APIs
56. NeurIPS 2024Grammar-Aligned Decoding
57. NeurIPS 2024Grasp as You Say: Language-guided Dexterous Grasp Generation
58. NeurIPS 2024Guided Trajectory Generation with Diffusion Models for Offline Model-based Optimization
59. NeurIPS 2024Guiding a Diffusion Model with a Bad Version of Itself
60. NeurIPS 2024HARMONIC: Harnessing LLMs for Tabular Data Synthesis and Privacy Protection
61. NeurIPS 2024Hierarchical Programmatic Option Framework
62. NeurIPS 2024Hints-In-Browser: Benchmarking Language Models for Programming Feedback Generation
63. NeurIPS 2024HumanVid: Demystifying Training Data for Camera-controllable Human Image Animation
64. NeurIPS 2024Hypothesis Testing the Circuit Hypothesis in LLMs
65. NeurIPS 2024IaC-Eval: A Code Generation Benchmark for Cloud Infrastructure-as-Code Programs
66. NeurIPS 2024IDGen: Item Discrimination Induced Prompt Generation for LLM Evaluation
67. NeurIPS 2024IF-Font: Ideographic Description Sequence-Following Font Generation
68. NeurIPS 2024Image Understanding Makes for A Good Tokenizer for Image Generation
69. NeurIPS 2024IMAGPose: A Unified Conditional Framework for Pose-Guided Person Generation
70. NeurIPS 2024Improved Distribution Matching Distillation for Fast Image Synthesis
71. NeurIPS 2024Improved Generation of Adversarial Examples Against Safety-aligned LLMs
72. NeurIPS 2024INDICT: Code Generation with Internal Dialogues of Critiques for Both Security and Helpfulness
73. NeurIPS 2024InfiBench: Evaluating the Question-Answering Capabilities of Code Large Language Models
74. NeurIPS 2024IntraMix: Intra-Class Mixup Generation for Accurate Labels and Neighbors
75. NeurIPS 2024IRCAN: Mitigating Knowledge Conflicts in LLM Generation via Identifying and Reweighting Context-Aware Neurons
76. NeurIPS 2024Is Programming by Example Solved by LLMs?
77. NeurIPS 2024kGym: A Platform and Dataset to Benchmark Large Language Models on Linux Kernel Crash Resolution
78. NeurIPS 2024Language Generation in the Limit
79. NeurIPS 2024Language Without Borders: A Dataset and Benchmark for Code-Switching Lip Reading
80. NeurIPS 2024Language-Driven Interactive Traffic Trajectory Generation
81. NeurIPS 2024Learning to Reason via Program Generation, Emulation, and Search
82. NeurIPS 2024LeDex: Training LLMs to Better Self-Debug and Explain Code
83. NeurIPS 2024LLMDFA: Analyzing Dataflow in Code with Large Language Models
84. NeurIPS 2024Mercury: A Code Efficiency Benchmark for Code Large Language Models
85. NeurIPS 2024MILP-StuDio: MILP Instance Generation via Block Structure Decomposition
86. NeurIPS 2024MSA Generation with Seqs2Seqs Pretraining: Advancing Protein Structure Predictions
87. NeurIPS 2024Natural Counterfactuals With Necessary Backtracking
88. NeurIPS 2024Nearest Neighbor Speculative Decoding for LLM Generation and Attribution
89. NeurIPS 2024Neural Residual Diffusion Models for Deep Scalable Vision Generation
90. NeurIPS 2024NovoBench: Benchmarking Deep Learning-based \emph{De Novo} Sequencing Methods in Proteomics
91. NeurIPS 2024OneActor: Consistent Subject Generation via Cluster-Conditioned Guidance
92. NeurIPS 2024Optimized Feature Generation for Tabular Data via LLMs with Decision Tree Reasoning
93. NeurIPS 2024Order-Independence Without Fine Tuning
94. NeurIPS 2024PhyloGen: Language Model-Enhanced Phylogenetic Inference via Graph Structure Generation
95. NeurIPS 2024Predictive Attractor Models
96. NeurIPS 2024Protecting Your LLMs with Information Bottleneck
97. NeurIPS 2024PuLID: Pure and Lightning ID Customization via Contrastive Alignment
98. NeurIPS 2024QuaRot: Outlier-Free 4-Bit Inference in Rotated LLMs
99. NeurIPS 2024QVAE-Mole: The Quantum VAE with Spherical Latent Variable Learning for 3-D Molecule Generation
100. NeurIPS 2024Rad-NeRF: Ray-decoupled Training of Neural Radiance Field

FAQ

How many Code Generation papers were published at NeurIPS, ICLR, ICML and CVPR from 2023 to 2026?

2,161 in total: 210 in 2023, 446 in 2024, 645 in 2025, 860 in 2026.

How many Code Generation papers are at NeurIPS 2026?

NeurIPS 2026 has 236 Code Generation papers, versus 230 the year before.

How many Code Generation papers are at ICLR 2026?

ICLR 2026 has 241 Code Generation papers, versus 164 the year before.

How many Code Generation papers are at ICML 2026?

ICML 2026 has 174 Code Generation papers, versus 79 the year before.

How many Code Generation papers are at CVPR 2026?

CVPR 2026 has 209 Code Generation papers, versus 172 the year before.

Which conference publishes the most Code Generation papers?

NeurIPS, with 630 papers from 2023 to 2026.