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 3 / 5 页

101. NeurIPS 2025Searching Latent Program Spaces
102. NeurIPS 2025Single-pass Adaptive Image Tokenization for Minimum Program Search
103. NeurIPS 2025TF-MAS: Training-free Mamba2 Architecture Search
104. NeurIPS 2025Training Language Models to Generate Quality Code with Program Analysis Feedback
105. CVPR 20243D Facial Expressions through Analysis-by-Neural-Synthesis
106. CVPR 2024AlignMiF: Geometry-Aligned Multimodal Implicit Field for LiDAR-Camera Joint Synthesis
107. CVPR 2024AnyScene: Customized Image Synthesis with Composited Foreground
108. CVPR 2024Coherent Temporal Synthesis for Incremental Action Segmentation
109. CVPR 2024Compressed 3D Gaussian Splatting for Accelerated Novel View Synthesis
110. CVPR 2024DART: Implicit Doppler Tomography for Radar Novel View Synthesis
111. CVPR 2024Fairy: Fast Parallelized Instruction-Guided Video-to-Video Synthesis
112. CVPR 2024G-NeRF: Geometry-enhanced Novel View Synthesis from Single-View Images
113. CVPR 2024Generalizable Novel-View Synthesis using a Stereo Camera
114. CVPR 2024Improving Subject-Driven Image Synthesis with Subject-Agnostic Guidance
115. CVPR 2024In Search of a Data Transformation That Accelerates Neural Field Training
116. CVPR 2024In-distribution Public Data Synthesis with Diffusion Models for Differentially Private Image Classification
117. CVPR 2024Is Vanilla MLP in Neural Radiance Field Enough for Few-shot View Synthesis?
118. CVPR 2024Learning Dynamic Tetrahedra for High-Quality Talking Head Synthesis
119. CVPR 2024Neural Refinement for Absolute Pose Regression with Feature Synthesis
120. CVPR 2024Novel View Synthesis with View-Dependent Effects from a Single Image
121. CVPR 2024PhyScene: Physically Interactable 3D Scene Synthesis for Embodied AI
122. CVPR 2024Rethinking the Objectives of Vector-Quantized Tokenizers for Image Synthesis
123. CVPR 2024SceneTex: High-Quality Texture Synthesis for Indoor Scenes via Diffusion Priors
124. CVPR 2024Self-Training Large Language Models for Improved Visual Program Synthesis With Visual Reinforcement
125. CVPR 2024SuperSVG: Superpixel-based Scalable Vector Graphics Synthesis
126. CVPR 2024SyncTalk: The Devil is in the Synchronization for Talking Head Synthesis
127. CVPR 2024Towards Generalizable Tumor Synthesis
128. CVPR 2024Unlocking Pre-trained Image Backbones for Semantic Image Synthesis
129. CVPR 2024Video Frame Interpolation via Direct Synthesis with the Event-based Reference
130. CVPR 2024XScale-NVS: Cross-Scale Novel View Synthesis with Hash Featurized Manifold
131. ICLR 2024A Real-World WebAgent with Planning, Long Context Understanding, and Program Synthesis
132. ICLR 2024Advancing Pose-Guided Image Synthesis with Progressive Conditional Diffusion Models
133. ICLR 2024ExeDec: Execution Decomposition for Compositional Generalization in Neural Program Synthesis
134. ICLR 2024Generating Pragmatic Examples to Train Neural Program Synthesizers
135. ICLR 2024Is Self-Repair a Silver Bullet for Code Generation?
136. ICLR 2024Learning to Solve Bilevel Programs with Binary Tender
137. ICML 2024Amortizing Pragmatic Program Synthesis with Rankings
138. ICML 2024Approximate Nearest Neighbor Search with Window Filters
139. ICML 2024Bayesian Program Learning by Decompiling Amortized Knowledge
140. ICML 2024Emergent Representations of Program Semantics in Language Models Trained on Programs
141. ICML 2024Exploiting Code Symmetries for Learning Program Semantics
142. ICML 2024Scalable High-Resolution Pixel-Space Image Synthesis with Hourglass Diffusion Transformers
143. NeurIPS 2024Double-Ended Synthesis Planning with Goal-Constrained Bidirectional Search
144. NeurIPS 2024Hierarchical Programmatic Option Framework
145. NeurIPS 2024HYSYNTH: Context-Free LLM Approximation for Guiding Program Synthesis
146. NeurIPS 2024Is Programming by Example Solved by LLMs?
147. NeurIPS 2024Learning to Edit Visual Programs with Self-Supervision
148. NeurIPS 2024SEEV: Synthesis with Efficient Exact Verification for ReLU Neural Barrier Functions
149. NeurIPS 2024Speculative Monte-Carlo Tree Search
150. NeurIPS 2024Symbolic Regression with a Learned Concept Library

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。