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 208 篇，第 2 / 5 页

51. NeurIPS 2026GPU-Accelerated Synthesis of Mixed-Boolean Arithmetic: Beyond Caching
52. NeurIPS 2026Inductive Deductive Synthesis: Enabling AI to Generate Formally Verified Systems
53. NeurIPS 2026Learn Locally, Recurse Globally: Neural Circuit Synthesis Beyond Training Depth
54. NeurIPS 2026NeuroSynTheos: Learning to accelerate counterexample-guided reactive synthesis modulo theories
55. NeurIPS 2026Panoptic Scene Program Diffusion Transformer
56. NeurIPS 2026Program-as-Weights: A Programming Paradigm for Fuzzy Functions
57. NeurIPS 2026Property-Guided LLM Program Synthesis for Planning
58. NeurIPS 2026StereoSplat: Metric-Scale Novel View Synthesis via Stereo-Grounded Gaussian Splatting
59. NeurIPS 2026UniSHARP: Universal Sharp Monocular View Synthesis
60. CVPR 2025BimArt: A Unified Approach for the Synthesis of 3D Bimanual Interaction with Articulated Objects
61. CVPR 2025CoMapGS: Covisibility Map-based Gaussian Splatting for Sparse Novel View Synthesis
62. CVPR 2025Data Synthesis with Diverse Styles for Face Recognition via 3DMM-Guided Diffusion
63. CVPR 2025Design2GarmentCode: Turning Design Concepts to Tangible Garments Through Program Synthesis
64. CVPR 2025DiffPortrait360: Consistent Portrait Diffusion for 360 View Synthesis
65. CVPR 2025DreamText: High Fidelity Scene Text Synthesis
66. CVPR 2025EVPGS: Enhanced View Prior Guidance for Splatting-based Extrapolated View Synthesis
67. CVPR 2025FrugalNeRF: Fast Convergence for Extreme Few-shot Novel View Synthesis without Learned Priors
68. CVPR 2025GenDeg: Diffusion-based Degradation Synthesis for Generalizable All-In-One Image Restoration
69. CVPR 2025Img-Diff: Contrastive Data Synthesis for Multimodal Large Language Models
70. CVPR 2025Learning-enabled Polynomial Lyapunov Function Synthesis via High-Accuracy Counterexample-Guided Framework
71. CVPR 2025NexusGS: Sparse View Synthesis with Epipolar Depth Priors in 3D Gaussian Splatting
72. CVPR 2025Novel View Synthesis with Pixel-Space Diffusion Models
73. CVPR 2025PanSplat: 4K Panorama Synthesis with Feed-Forward Gaussian Splatting
74. CVPR 2025RainyGS: Efficient Rain Synthesis with Physically-Based Gaussian Splatting
75. CVPR 2025Retrieving Semantics from the Deep: an RAG Solution for Gesture Synthesis
76. CVPR 2025SoundVista: Novel-View Ambient Sound Synthesis via Visual-Acoustic Binding
77. CVPR 2025VasTSD: Learning 3D Vascular Tree-state Space Diffusion Model for Angiography Synthesis
78. ICLR 2025Diffusion On Syntax Trees For Program Synthesis
79. ICLR 2025Execution-guided within-prompt search for programming-by-example
80. ICLR 2025h4rm3l: A Language for Composable Jailbreak Attack Synthesis
81. ICLR 2025Looking Backward: Retrospective Backward Synthesis for Goal-Conditioned GFlowNets
82. ICLR 2025STAR: Synthesis of Tailored Architectures
83. ICML 2025High Dynamic Range Novel View Synthesis with Single Exposure
84. ICML 2025Self-Improving Language Models for Evolutionary Program Synthesis: A Case Study on ARC-AGI
85. NeurIPS 2025AlgoTune: Can Language Models Speed Up General-Purpose Numerical Programs?
86. NeurIPS 2025BIPNN: Learning to Solve Binary Integer Programming via Hypergraph Neural Networks
87. NeurIPS 2025Dynamic View Synthesis as an Inverse Problem
88. NeurIPS 2025EnCompass: Enhancing Agent Programming with Search Over Program Execution Paths
89. NeurIPS 2025GSRF: Complex-Valued 3D Gaussian Splatting for Efficient Radio-Frequency Data Synthesis
90. NeurIPS 2025HoliGS: Holistic Gaussian Splatting for Embodied View Synthesis
91. NeurIPS 2025HyPlaneHead: Rethinking Tri-plane-like Representations in Full-Head Image Synthesis
92. NeurIPS 2025Learning Neural Exposure Fields for View Synthesis
93. NeurIPS 2025LongMagpie: A Self-synthesis Method for Generating Large-scale Long-context Instructions
94. NeurIPS 2025Native-Resolution Image Synthesis
95. NeurIPS 2025Neural Attention Search
96. NeurIPS 2025Once Upon an Input: Reasoning via Per-Instance Program Synthesis
97. NeurIPS 2025PoE-World: Compositional World Modeling with Products of Programmatic Experts
98. NeurIPS 2025Point Cloud Synthesis Using Inner Product Transforms
99. NeurIPS 2025Program Synthesis via Test-Time Transduction
100. NeurIPS 2025RoomEditor: High-Fidelity Furniture Synthesis with Parameter-Sharing U-Net

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。