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

241 papers, page 2 of 5

51. ICLR 2026Cross-ControlNet: Training-Free Fusion of Multiple Conditions for Text-to-Image Generation
52. ICLR 2026CrossPL: Systematic Evaluation of Large Language Models for Cross Programming Language Interoperating Code Generation
53. ICLR 2026CTBench: Cryptocurrency Time Series Generation Benchmark
54. ICLR 2026DAComp: Benchmarking Data Agents across the Full Data Intelligence Lifecycle
55. ICLR 2026Data Provenance for Image Auto-Regressive Generation
56. ICLR 2026DCFold: Efficient Protein Structure Generation with Single Forward Pass
57. ICLR 2026DeepRAG: Thinking to Retrieve Step by Step for Large Language Models
58. ICLR 2026DELTA-Code: How RL Unlocks and Transfers New Programming Algorithms in LLMs
59. ICLR 2026DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation
60. ICLR 2026Diffusion Language Model Knows the Answer Before It Decodes
61. ICLR 2026Diffusion LLMs Can Do Faster-Than-AR Inference via Discrete Diffusion Forcing
62. ICLR 2026Directional Textual Inversion for Personalized Text-to-Image Generation
63. ICLR 2026Disentangled Hierarchical VAE for 3D Human-Human Interaction Generation
64. ICLR 2026DistillKac: Few-Step Image Generation via Damped Wave Equations
65. ICLR 2026Do LLMs Forget What They Should? Evaluating In-Context Forgetting in Large Language Models
66. ICLR 2026Don't Throw Away Your Pretrained Model
67. ICLR 2026DreamOn: Diffusion Language Models For Code Infilling Beyond Fixed-size Canvas
68. ICLR 2026EasyTune: Efficient Step-Aware Fine-Tuning for Diffusion-Based Motion Generation
69. ICLR 2026ELLMob: Event-Driven Human Mobility Generation with Self-Aligned LLM Framework
70. ICLR 2026Energy-Efficient Random Variate Generation via Compressed Lookup Tables
71. ICLR 2026Enhancing Instruction Following of LLMs via Activation Steering with Dynamic Rejection
72. ICLR 2026Enhancing Trustworthiness of Fine-Tuned LLMs via Regularized Subset Selection
73. ICLR 2026Equilibrium Language Models
74. ICLR 2026Event-T2M: Event-level Conditioning for Complex Text-to-Motion Synthesis
75. ICLR 2026Evolving Graph Structured Programs for Circuit Generation with Large Language Models
76. ICLR 2026ExpertLongBench: Benchmarking Language Models on Expert-Level Long-Form Generation Tasks with Structured Checklists
77. ICLR 2026Exploring Diverse Generation Paths via Inference-time Stiefel Activation Steering
78. ICLR 2026FACM: Flow-Anchored Consistency Models
79. ICLR 2026FHE-Coder: Secure Agentic Code Generation for Fully Homomorphic Encryption
80. ICLR 2026Figma2Code: Automating Multimodal Design to Code in the Wild
81. ICLR 2026Flow Caching for Autoregressive Video Generation
82. ICLR 2026From Large to Small: Transferring CUDA Optimization Expertise via Reasoning Graph
83. ICLR 2026From Prediction to Perfection: Introducing Refinement to Autoregressive Image Generation
84. ICLR 2026From Reproduction to Replication: Evaluating Research Agents with Progressive Code Masking
85. ICLR 2026From Verifiable Dot to Reward Chain: Harnessing Verifiable Reference-based Rewards for Reinforcement Learning of Open-ended Generation
86. ICLR 2026FullPart: Generating each 3D Part at Full Resolution
87. ICLR 2026FutureFill: Fast Generation from Convolutional Sequence Models
88. ICLR 2026GarmentGPT: Compositional Garment Pattern Generation via Discrete Latent Tokenization
89. ICLR 2026Generalizable Heuristic Generation Through LLMs with Meta-Optimization
90. ICLR 2026Generate Any Scene: Scene Graph Driven Data Synthesis for Visual Generation Training
91. ICLR 2026Generation then Reconstruction: Accelerating Masked Autoregressive Models via Two-Stage Sampling
92. ICLR 2026Gradient-Based Program Synthesis with Neurally Interpreted Languages
93. ICLR 2026GuidedSampling: Steering LLMs Towards Diverse Candidate Solutions at Inference-Time
94. ICLR 2026Gumbel Distillation for Parallel Text Generation
95. ICLR 2026HARDTESTGEN: A High-Quality RL Verifier Generation Pipeline for LLM Algorithimic Coding
96. ICLR 2026Harpoon: Generalised Manifold Guidance for Conditional Tabular Diffusion
97. ICLR 2026Helmsman: Autonomous Synthesis of Federated Learning Systems via Collaborative LLM Agents
98. ICLR 2026HeuriGym: An Agentic Benchmark for LLM-Crafted Heuristics in Combinatorial Optimization
99. ICLR 2026HiddenEcho: Mitigating Noise Amplification in Differentially Private LLMs with Hidden-State Correction
100. ICLR 2026HOG-Diff: Higher-Order Guided Diffusion for Graph Generation

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.