高斯过程论文趋势 2023–2026

主要结论

• 高斯过程论文从 2023 年的 154 篇增长到 2026 年的 341 篇，三年间扩大到约 2.2 倍。
• NeurIPS 是发高斯过程论文最多的会议，2023–2026 年共 372 篇，占四个会议总量的 35%。
• 交叉方向里涨得最快的是三维视觉：同时属于两个主题的论文从 2023 年的 0 篇增至 2026 年的 158 篇。
• 在「概率与贝叶斯」的 5 个主题里，它的 2026 年论文数排第 1；同组增长最快的生成流是 1.9 倍，高斯过程是 2.2 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 2026Adaptive Prior Selection in Gaussian Process Bandits with Thompson Sampling
• ICML 2026A unified theory of feature learning in RNNs and DNNs
• ICLR 2026Adaptive Gaussian Expansion for On-the-fly Category Discovery
• CVPR 2026Distilling Unsigned Distance Function for Surface Reconstruction from 3D Gaussian
• NeurIPS 2025Accelerated Evolving Set Processes for Local PageRank Computation
• ICML 2025BARK: A Fully Bayesian Tree Kernel for Black-box Optimization
• ICLR 2025Boosting Methods for Interval-censored Data with Regression and Classification
• CVPR 20253D Gaussian Head Avatars with Expressive Dynamic Appearances by Compact Tensorial Representations
• NeurIPS 2024Numerically Stable Sparse Gaussian Processes via Minimum Separation using Cover Trees
• ICML 2024A Rate-Distortion View of Uncertainty Quantification
• ICLR 2024A General Framework for User-Guided Bayesian Optimization
• CVPR 2024Deep Imbalanced Regression via Hierarchical Classification Adjustment
• NeurIPS 2023A Bayesian Take on Gaussian Process Networks
• ICML 2023Are Gaussian Data All You Need? The Extents and Limits of Universality in High-Dimensional Generalized Linear Estimation
• ICLR 2023Accurate Bayesian Meta-Learning by Accurate Task Posterior Inference
• CVPR 2023Robust and Scalable Gaussian Process Regression and Its Applications
• NeurIPS 2026Amortized Structured Stochastic Variational Inference for Gaussian Process Latent Variable Models
• ICML 2026ALAS: Additive Learnable Alpha-Stable Kernels for Flexible Bayesian Optimization
• ICLR 2026Continuous multinomial logistic regression for neural decoding
• CVPR 2026ELITE Efficient Gaussian Head Avatar from a Monocular Video via

全部高斯过程论文

共 372 篇，第 3 / 8 页

101. NeurIPS 2026U-MVP: Encode Locally, Decode Globally for Feed-Forward 3D Gaussian Splatting
102. NeurIPS 2026UltraVoxelGS: Voxel-First Feed-Forward Gaussian Splatting for 3D Ultrasound Reconstruction
103. NeurIPS 2026Umbilic Multinomial Logistic Regression
104. NeurIPS 2026UniGS: Unified Geometry-Aware Gaussian Splatting for Multimodal Rendering
105. NeurIPS 2026Very Fast Bayesian Additive Regression Trees on GPU
106. NeurIPS 2026When does LeJEPA learn a World Model?
107. NeurIPS 2025$\text{G}^2\text{M}$: A Generalized Gaussian Mirror Method to Boost Feature Selection Power
108. NeurIPS 20251000+ FPS 4D Gaussian Splatting for Dynamic Scene Rendering
109. NeurIPS 20253D Gaussian Flats: Hybrid 2D/3D Photometric Scene Reconstruction
110. NeurIPS 20253D-Prover: Diversity Driven Theorem Proving With Determinantal Point Processes
111. NeurIPS 20254DGT: Learning a 4D Gaussian Transformer Using Real-World Monocular Videos
112. NeurIPS 2025A Provable Approach for End-to-End Safe Reinforcement Learning
113. NeurIPS 2025Abstract Rendering: Certified Rendering Under 3D Semantic Uncertainty
114. NeurIPS 2025Accelerated Evolving Set Processes for Local PageRank Computation
115. NeurIPS 2025Achieving $\tilde{\mathcal{O}}(1/N)$ Optimality Gap in Restless Bandits through Gaussian Approximation
116. NeurIPS 2025Adaptive Kernel Design for Bayesian Optimization Is a Piece of CAKE with LLMs
117. NeurIPS 2025Addressing Mark Imbalance in Integration-free Marked Temporal Point Processes
118. NeurIPS 2025Anti-Aliased 2D Gaussian Splatting
119. NeurIPS 2025Approximation and Generalization Abilities of Score-based Neural Network Generative Models for Sub-Gaussian Distributions
120. NeurIPS 2025Assessing the quality of denoising diffusion models in Wasserstein distance: noisy score and optimal bounds
121. NeurIPS 2025AtlasGS: Atlanta-world Guided Surface Reconstruction with Implicit Structured Gaussians
122. NeurIPS 2025Autoregressive Motion Generation with Gaussian Mixture-Guided Latent Sampling
123. NeurIPS 2025BecomingLit: Relightable Gaussian Avatars with Hybrid Neural Shading
124. NeurIPS 2025BevSplat: Resolving Height Ambiguity via Feature-Based Gaussian Primitives for Weakly-Supervised Cross-View Localization
125. NeurIPS 2025Bivariate Matrix-valued Linear Regression (BMLR): Finite-sample performance under Identifiability and Sparsity Assumptions
126. NeurIPS 2025CGS-GAN: 3D Consistent Gaussian Splatting GANs for High Resolution Human Head Synthesis
127. NeurIPS 2025Deep Gaussian from Motion: Exploring 3D Geometric Foundation Models for Gaussian Splatting
128. NeurIPS 2025DEGauss: Defending Against Malicious 3D Editing for Gaussian Splatting
129. NeurIPS 2025DGH: Dynamic Gaussian Hair
130. NeurIPS 2025Distance-informed Neural Processes
131. NeurIPS 2025DrivingRecon: Large 4D Gaussian Reconstruction Model For Autonomous Driving
132. NeurIPS 2025Dynamic Gaussian Splatting from Defocused and Motion-blurred Monocular Videos
133. NeurIPS 2025EF-3DGS: Event-Aided Free-Trajectory 3D Gaussian Splatting
134. NeurIPS 2025Efficient Training of Minimal and Maximal Low-Rank Recurrent Neural Networks
135. NeurIPS 2025EGGS: Exchangeable 2D/3D Gaussian Splatting for Geometry-Appearance Balanced Novel View Synthesis
136. NeurIPS 2025Faster Fixed-Point Methods for Multichain MDPs
137. NeurIPS 2025FHGS: Feature-Homogenized Gaussian Splatting
138. NeurIPS 2025Flow Matching Neural Processes
139. NeurIPS 2025Gaussian Approximation and Concentration of Constant Learning-Rate Stochastic Gradient Descent
140. NeurIPS 2025Gaussian Herding across Pens: An Optimal Transport Perspective on Global Gaussian Reduction for 3DGS
141. NeurIPS 2025Gaussian Process Upper Confidence Bound Achieves Nearly-Optimal Regret in Noise-Free Gaussian Process Bandits
142. NeurIPS 2025Gaussian Processes for Shuffled Regression
143. NeurIPS 2025Gaussian Regression-Driven Tensorized Incomplete Multi-View Clustering with Dual Manifold Regularization
144. NeurIPS 2025Go With the Flow: Fast Diffusion for Gaussian Mixture Models
145. NeurIPS 2025GSRF: Complex-Valued 3D Gaussian Splatting for Efficient Radio-Frequency Data Synthesis
146. NeurIPS 2025H3D-DGS: Exploring Heterogeneous 3D Motion Representation for Deformable 3D Gaussian Splatting
147. NeurIPS 2025HAIF-GS: Hierarchical and Induced Flow-Guided Gaussian Splatting for Dynamic Scene
148. NeurIPS 2025HoliGS: Holistic Gaussian Splatting for Embodied View Synthesis
149. NeurIPS 2025Holistic Large-Scale Scene Reconstruction via Mixed Gaussian Splatting
150. NeurIPS 2025How Data Mixing Shapes In-Context Learning: Asymptotic Equivalence for Transformers with MLPs

常见问题

2023–2026 年四大会议一共有多少篇高斯过程论文？

共 1,049 篇，按年份分别是 2023 年 154 篇、2024 年 231 篇、2025 年 323 篇、2026 年 341 篇。

NeurIPS 2026 有多少篇高斯过程论文？

NeurIPS 2026 有 106 篇高斯过程论文，上一届是 106 篇。

ICLR 2026 有多少篇高斯过程论文？

ICLR 2026 有 40 篇高斯过程论文，上一届是 41 篇。

ICML 2026 有多少篇高斯过程论文？

ICML 2026 有 79 篇高斯过程论文，上一届是 53 篇。

CVPR 2026 有多少篇高斯过程论文？

CVPR 2026 有 116 篇高斯过程论文，上一届是 123 篇。

哪个会议的高斯过程论文最多？

NeurIPS，2023–2026 年共 372 篇。