Code Generation papers, 2023–2026
Program synthesis and code LLMs
Scope: NeurIPS, ICLR, ICML and CVPR, 2023–2026. 2,161 papers are tagged with this topic.
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.
Papers per venue
Counts by year and venue
| Year | NeurIPS | ICLR | ICML | CVPR | Total |
|---|---|---|---|---|---|
| 2023 | 29 | 55 | 31 | 95 | 210 |
| 2024 | 135 | 66 | 111 | 134 | 446 |
| 2025 | 230 | 164 | 79 | 172 | 645 |
| 2026 | 236 | 241 | 174 | 209 | 860 |
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
2,161 papers, page 5 of 44
- CVPR 2026VecGlypher Unified Vector Glyph Generation with Language Models
- CVPR 2026ViLearn Accelerating Training Convergence of Image-to-3D Generation via Visibility Learning
- CVPR 2026VisiLock Authorizing Instruction-based Image editing with Dual Score Distillation
- CVPR 2026VVS Accelerating Speculative Decoding for Visual Autoregressive Generation via Partial
- CVPR 2026Widget2Code From Visual Widgets to UI Code via Multimodal LLMs
- CVPR 2026WonderZoom Multi-Scale 3D World Generation
- CVPR 2026You Only Erase Once Erasing Anything without Bringing Unexpected Content
- CVPR 2026Your Classifier Can Do More Towards Balancing the Gaps in
- CVPR 2026Zero-Shot Image Denoising via Hybrid Prior-Guided Pseudo Sample Generation
- ICLR 2026$\textit{MADFormer}$: Mixed Autoregressive and Diffusion Transformers for Continuous Image Generation
- ICLR 2026A Bayesian Nonparametric Framework for Private, Fair, and Balanced Tabular Data Synthesis
- ICLR 2026A Noise is Worth Diffusion Guidance
- ICLR 2026A Problem-Oriented Perspective and Anchor Verification for Code Optimization
- ICLR 2026Accelerating Eigenvalue Dataset Generation via Chebyshev Subspace Filter
- ICLR 2026Addressing Pitfalls in the Evaluation of Uncertainty Estimation Methods for Natural Language Generation
- ICLR 2026AetherCode: Evaluating LLMs’ Ability to Win In Premier Programming Competitions
- ICLR 2026AgentSynth: Scalable Task Generation for Generalist Computer-Use Agents
- ICLR 2026Agnostics: Learning to Synthesize Code in Any Programming Language with a Universal Reinforcement Learning Environment
- ICLR 2026AI-for-Science Low-code Platform with Bayesian Adversarial Multi-Agent Framework
- ICLR 2026Algorithm Generation via Creative Ideation
- ICLR 2026Alignment through Meta-Weighted Online Sampling: Bridging the Gap between Data Generation and Preference Optimization
- ICLR 2026All Code, No Thought: Language Models Struggle to Reason in Ciphered Language
- ICLR 2026An Agentic Framework with LLMs for Solving Complex Vehicle Routing Problems
- ICLR 2026Antislop: A Comprehensive Framework for Identifying and Eliminating Repetitive Patterns in Language Models
- ICLR 2026Any-Order Any-Subset AutoRegressive Model
- ICLR 2026Any-step Generation via N-th Order Recursive Consistent Velocity Field Estimation
- ICLR 2026APT: Towards Universal Scene Graph Generation via Plug-in Adaptive Prompt Tuning
- ICLR 2026Aria: an Agent for Retrieval and Iterative Auto-Formalization via Dependency Graph
- ICLR 2026AssetFormer: Modular 3D Assets Generation with Autoregressive Transformer
- ICLR 2026ATGen: Adversarial Reinforcement Learning for Test Case Generation
- ICLR 2026Attention Is All You Need for KV Cache in Diffusion LLMs
- ICLR 2026Attention Sinks and Compression Valleys in LLMs are Two Sides of the Same Coin
- ICLR 2026AutoCode: LLMs as Problem Setters for Competitive Programming
- ICLR 2026AutoCodeBench: Large Language Models are Automatic Code Benchmark Generators
- ICLR 2026Automated Formalization via Conceptual Retrieval-Augmented LLMs
- ICLR 2026Autoregressive Image Generation with Randomized Parallel Decoding
- ICLR 2026BAR: Refactor the Basis of Autoregressive Visual Generation
- ICLR 2026Benchmarking Overton Pluralism in LLMs
- ICLR 2026Best-of-Infinity: Asymptotic Performance of Test-Time Compute
- ICLR 2026Beyond Distributions: Geometric Action Control for Continuous Reinforcement Learning
- ICLR 2026BézierFlow: Learning Bézier Stochastic Interpolant Schedulers for Few-Step Generation
- ICLR 2026BIRD-INTERACT: Re-imagining Text-to-SQL Evaluation via Lens of Dynamic Interactions
- ICLR 2026Breaking the SFT Plateau: Multimodal Structured Reinforcement Learning for Chart-to-Code Generation
- ICLR 2026Bures-Wasserstein Flow Matching for Graph Generation
- ICLR 2026Cache What Lasts: Token Retention for Memory-Bounded KV Cache in LLMs
- ICLR 2026Cactus: Accelerating Auto-Regressive Decoding with Constrained Acceptance Speculative Sampling
- ICLR 2026Can LLMs Reason Soundly in Law? Auditing Inference Patterns for Legal Judgment
- ICLR 2026Cautious Optimizers: Improving Training with One Line of Code
- ICLR 2026ChartGalaxy: A Dataset for Infographic Chart Understanding and Generation
- ICLR 2026CLARC: C/C++ Benchmark for Robust Code Search
Ask about this trend from Claude or Cursor
Connect the Paperlist MCP and your assistant can pull the numbers on this page while you draft a survey, pick a direction or plan a submission: papers per year and venue, growth, the fastest-rising sub-themes and representative papers, shaped around your question.
Copy this prompt into your assistant
Use paperlist to show how Code Generation papers grew at NeurIPS from 2023 to 2026, and which year jumped the most.
Tool the assistant calls: get_topic_stats {"topic": "code-generation"}
Set up Paperlist MCP in two minutes (Claude Code, Cursor, Codex, ChatGPT)
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.