神经程序综合论文趋势 2023–2026

主要结论

• 神经程序综合论文从 2023 年的 57 篇增长到 2026 年的 59 篇，三年间扩大到约 1.0 倍。
• CVPR 是发神经程序综合论文最多的会议，2023–2026 年共 89 篇，占四个会议总量的 43%。
• 交叉方向里涨得最快的是驾驶仿真：同时属于两个主题的论文从 2023 年的 5 篇增至 2026 年的 10 篇。
• 在「程序综合」的 5 个主题里，它的 2026 年论文数排第 2；同组增长最快的定理证明是 13 倍，神经程序综合是 1.0 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 2026Feedforward Novel View Synthesis for Heterogeneous Cameras
• ICML 2026Search Space Synthesis for Parametric Functions
• ICLR 2026LLM as an Algorithmist: Enhancing Anomaly Detectors via Programmatic Synthesis
• CVPR 2026Beyond Geometry Artistic Disparity Synthesis for Immersive 2D-to-3D
• NeurIPS 2025AlgoTune: Can Language Models Speed Up General-Purpose Numerical Programs?
• ICML 2025High Dynamic Range Novel View Synthesis with Single Exposure
• ICLR 2025Execution-guided within-prompt search for programming-by-example
• CVPR 2025BimArt: A Unified Approach for the Synthesis of 3D Bimanual Interaction with Articulated Objects
• NeurIPS 2024HYSYNTH: Context-Free LLM Approximation for Guiding Program Synthesis
• ICML 2024Amortizing Pragmatic Program Synthesis with Rankings
• ICLR 2024Generating Pragmatic Examples to Train Neural Program Synthesizers
• CVPR 2024SuperSVG: Superpixel-based Scalable Vector Graphics Synthesis
• NeurIPS 2023Construction of Hierarchical Neural Architecture Search Spaces based on Context-free Grammars
• ICML 2023XAI Beyond Classification: Interpretable Neural Clustering
• ICLR 2023Language Models Can Teach Themselves to Program Better
• CVPR 2023Implicit Neural Head Synthesis via Controllable Local Deformation Fields
• NeurIPS 2026GPU-Accelerated Synthesis of Mixed-Boolean Arithmetic: Beyond Caching
• ICML 2026CHESS: Chebyshev Spectral Synthesis for Trajectory Condensation
• ICLR 2026RefineStat: Efficient Exploration for Probabilistic Program Synthesis
• CVPR 2026From Rays to Projections Better Inputs for Feed-Forward View Synthesis

全部神经程序综合论文

共 57 篇，第 1 / 2 页

1. CVPR 20233D-Aware Conditional Image Synthesis
2. CVPR 2023Balanced Spherical Grid for Egocentric View Synthesis
3. CVPR 2023CAMS: CAnonicalized Manipulation Spaces for Category-Level Functional Hand-Object Manipulation Synthesis
4. CVPR 2023Consistent View Synthesis With Pose-Guided Diffusion Models
5. CVPR 2023DyNCA: Real-Time Dynamic Texture Synthesis Using Neural Cellular Automata
6. CVPR 2023Efficient Scale-Invariant Generator With Column-Row Entangled Pixel Synthesis
7. CVPR 2023Enhanced Stable View Synthesis
8. CVPR 2023High-Fidelity Guided Image Synthesis With Latent Diffusion Models
9. CVPR 2023Implicit Neural Head Synthesis via Controllable Local Deformation Fields
10. CVPR 2023Learning 3D-Aware Image Synthesis With Unknown Pose Distribution
11. CVPR 2023MoDi: Unconditional Motion Synthesis From Diverse Data
12. CVPR 2023Mofusion: A Framework for Denoising-Diffusion-Based Motion Synthesis
13. CVPR 2023NeRFLix: High-Quality Neural View Synthesis by Learning a Degradation-Driven Inter-Viewpoint MiXer
14. CVPR 2023NeRFVS: Neural Radiance Fields for Free View Synthesis via Geometry Scaffolds
15. CVPR 2023Neural Texture Synthesis With Guided Correspondence
16. CVPR 2023Novel-View Acoustic Synthesis
17. CVPR 2023OmniAvatar: Geometry-Guided Controllable 3D Head Synthesis
18. CVPR 2023Painting 3D Nature in 2D: View Synthesis of Natural Scenes From a Single Semantic Mask
19. CVPR 2023PanoHead: Geometry-Aware 3D Full-Head Synthesis in 360deg
20. CVPR 2023Person Image Synthesis via Denoising Diffusion Model
21. CVPR 2023Progressive Disentangled Representation Learning for Fine-Grained Controllable Talking Head Synthesis
22. CVPR 2023Progressively Optimized Local Radiance Fields for Robust View Synthesis
23. CVPR 2023Regularized Vector Quantization for Tokenized Image Synthesis
24. CVPR 2023SceneComposer: Any-Level Semantic Image Synthesis
25. CVPR 2023Top-Down Visual Attention From Analysis by Synthesis
26. ICLR 2023CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis
27. ICLR 2023Discrete Predictor-Corrector Diffusion Models for Image Synthesis
28. ICLR 2023Edge Guided GANs with Contrastive Learning for Semantic Image Synthesis
29. ICLR 2023Language Models Can Teach Themselves to Program Better
30. ICLR 2023Learning Sparse Group Models Through Boolean Relaxation
31. ICLR 2023Non-parametric Outlier Synthesis
32. ICLR 2023StyleMorph: Disentangled 3D-Aware Image Synthesis with a 3D Morphable StyleGAN
33. ICLR 2023View Synthesis with Sculpted Neural Points
34. ICML 2023Can Large Language Models Reason about Program Invariants?
35. ICML 2023CoDi: Co-evolving Contrastive Diffusion Models for Mixed-type Tabular Synthesis
36. ICML 2023PAL: Program-aided Language Models
37. ICML 2023Relevant Walk Search for Explaining Graph Neural Networks
38. ICML 2023XAI Beyond Classification: Interpretable Neural Clustering
39. NeurIPS 2023Construction of Hierarchical Neural Architecture Search Spaces based on Context-free Grammars
40. NeurIPS 2023DELIFFAS: Deformable Light Fields for Fast Avatar Synthesis
41. NeurIPS 2023DynPoint: Dynamic Neural Point For View Synthesis
42. NeurIPS 2023Enhancing Robot Program Synthesis Through Environmental Context
43. NeurIPS 2023Evolutionary Neural Architecture Search for Transformer in Knowledge Tracing
44. NeurIPS 2023Generalizable Lightweight Proxy for Robust NAS against Diverse Perturbations
45. NeurIPS 2023Graph Clustering with Graph Neural Networks
46. NeurIPS 2023Human spatiotemporal pattern learning as probabilistic program synthesis
47. NeurIPS 2023LambdaBeam: Neural Program Search with Higher-Order Functions and Lambdas
48. NeurIPS 2023LightSpeed: Light and Fast Neural Light Fields on Mobile Devices
49. NeurIPS 2023Mip-Grid: Anti-aliased Grid Representations for Neural Radiance Fields
50. NeurIPS 2023PanoGRF: Generalizable Spherical Radiance Fields for Wide-baseline Panoramas

常见问题

2023–2026 年四大会议一共有多少篇神经程序综合论文？

共 208 篇，按年份分别是 2023 年 57 篇、2024 年 47 篇、2025 年 45 篇、2026 年 59 篇。

NeurIPS 2026 有多少篇神经程序综合论文？

NeurIPS 2026 有 18 篇神经程序综合论文，上一届是 20 篇。

ICLR 2026 有多少篇神经程序综合论文？

ICLR 2026 有 11 篇神经程序综合论文，上一届是 5 篇。

ICML 2026 有多少篇神经程序综合论文？

ICML 2026 有 10 篇神经程序综合论文，上一届是 2 篇。

CVPR 2026 有多少篇神经程序综合论文？

CVPR 2026 有 20 篇神经程序综合论文，上一届是 18 篇。

哪个会议的神经程序综合论文最多？

CVPR，2023–2026 年共 89 篇。