通用机器学习 · supervised learning论文趋势 2023–2026

主要结论

• 通用机器学习 · supervised learning论文从 2023 年的 263 篇增长到 2026 年的 279 篇，三年间扩大到约 1.1 倍。
• NeurIPS 是发通用机器学习 · supervised learning论文最多的会议，2023–2026 年共 731 篇，占四个会议总量的 51%。
• 交叉方向里涨得最快的是扩散模型：同时属于两个主题的论文从 2023 年的 2 篇增至 2026 年的 9 篇。
• 在「通用机器学习」的 6 个主题里，它的 2026 年论文数排第 3；同组增长最快的通用机器学习 · evaluation是 4.3 倍，通用机器学习 · supervised learning是 1.1 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 2026AOT-POT: Adaptive Operator Transformation for Large-Scale PDE Pre-training
• ICML 2026$\mathbb{R}^{2k}$ is Theoretically Large Enough for Embedding-based Top-$k$ Retrieval
• ICLR 2026Adaptive Concept Discovery for Interpretable Few-Shot Text Classification
• CVPR 2026Enabling Supervised Learning of Generative Signatures for Generalized AI-Generated Images
• NeurIPS 2025$\boldsymbol{\lambda}$-Orthogonality Regularization for Compatible Representation Learning
• ICML 2025Ab Initio Nonparametric Variable Selection for Scalable Symbolic Regression with Large $p$
• ICLR 2025Balanced Neural ODEs: nonlinear model order reduction and Koopman operator approximations
• CVPR 2025A Unified Framework for Heterogeneous Semi-supervised Learning
• NeurIPS 2024(FL)$^2$: Overcoming Few Labels in Federated Semi-Supervised Learning
• ICML 2024A New Branch-and-Bound Pruning Framework for $\ell_0$-Regularized Problems
• ICLR 2024A Study of Bayesian Neural Network Surrogates for Bayesian Optimization
• CVPR 2024Efficient Hyperparameter Optimization with Adaptive Fidelity Identification
• NeurIPS 2023A Graph-Theoretic Framework for Understanding Open-World Semi-Supervised Learning
• ICML 2023A Model-free Closeness-of-influence Test for Features in Supervised Learning
• ICLR 2023Deep Ranking Ensembles for Hyperparameter Optimization
• CVPR 2023Boosting Semi-Supervised Learning by Exploiting All Unlabeled Data
• NeurIPS 2026Approximation of Maximally Monotone Operators : A Graph Convergence Perspective
• ICML 2026Active Budget Allocation for Efficient Scaling Law Estimation via Surrogate-Guided Pruning
• ICLR 2026Buckingham $\pi$-Invariant Test‑Time Projection for Robust PDE Surrogate Modeling
• CVPR 2026HyperNAS Enhancing Architecture Representation for NAS Predictor via Hypernetwork

全部通用机器学习 · supervised learning论文

共 1,424 篇，第 4 / 29 页

151. ICML 2026Neural Collapse by Design: Learning Class Prototypes on the Hypersphere
152. ICML 2026Newton-coupled Dual-Teacher Semi-supervised Learning Framework
153. ICML 2026On the Power of Statistics in Class-Incremental Learning with Pretrained Models
154. ICML 2026On the Sample Efficiency of Inverse Dynamics Models for Semi-Supervised Imitation Learning
155. ICML 2026One Coin Has Two Sides: Single Poistive Multi Label Learning from Salient Annotations
156. ICML 2026Persistent Backdoor Attacks in Class-Incremental Learning via Structural Invariant Anchoring
157. ICML 2026Physics-informed Neural Operator Learning for Nonlinear Grad-Shafranov Equation
158. ICML 2026Pianist Transformer: Towards Expressive Piano Performance Rendering via Scalable Self-Supervised Pre-Training
159. ICML 2026PINE: Pruning Boosted Tree Ensembles with Conformal In-Distribution Prediction Equivalence
160. ICML 2026Quantitative Estimation of Target Task Performance from Unsupervised Pretext Task in Semi/Self-Supervised Learning
161. ICML 2026RECAST: Model Reconstruction via Counterfactual-Aware Wasserstein Geometry under Limited Data
162. ICML 2026Relevance-Based Embeddings: Lightweight Candidate Retrieval via Heavy-Ranker Calls
163. ICML 2026Risk-Bounded Distribution Reconstruction: Stable Statistic Calibration for Long-Tailed Recognition
164. ICML 2026Self-Supervised Learning as Discrete Communication
165. ICML 2026Semi-Supervised Gaze Estimation via Disentangled Subspace Contrastive Learning
166. ICML 2026Semi-Supervised Hypothesis Testing by Betting on Predictions
167. ICML 2026Semi-Supervised Learning for Molecular Graphs via Ensemble Consensus
168. ICML 2026Semi-Supervised Learning with Noisy Proxy Covariates: Generalization Bounds and Distribution Regression
169. ICML 2026Semi-Supervised Noise Adaptation: Transferring Knowledge from Noise Domain
170. ICML 2026Solving Time-Dependent Differential Equations with Physical Dynamical Systems
171. ICML 2026SOTAlign: Semi-Supervised Alignment of Unimodal Vision and Language Models via Optimal Transport
172. ICML 2026SpikeCLR: Self-Supervised Contrastive Learning for Visual Representations with Spiking Neural Networks
173. ICML 2026STAND: Self-Aware Precondition Induction for Interactive Task Learning
174. ICML 2026Stochastic Lifting for Generating Trajectories of Stochastic Physical Systems
175. ICML 2026TabularBERT: Binning-Based Self-Supervised Learning for Tabular Representation
176. ICML 2026Taking the GP Out of the Loop
177. ICML 2026The Extra Tokens Matter: Disentangled Representation Learning with Vision Transformers
178. ICML 2026Theoretical Guarantees for One-Shot Magnitude Pruning and Compute-Adaptive Early Exit
179. ICML 2026TN-SHAP-G: Graph-Structured Tensor Network Surrogates for Shapley Values and Interactions
180. ICML 2026Topology-Preserving Neural Operator Learning via Hodge Decomposition
181. ICML 2026Towards Theoretical Understanding of Transformer Test-Time Computing: Investigation on In-Context Linear Regression
182. ICML 2026Trajectory-Aware Certified Decentralized Unlearning via SGD Stability
183. ICML 2026Transformer Circuits Can Realize Clustering Algorithms
184. ICML 2026Transolver-3: Scaling Up Transformer Solvers to Industrial-Scale Geometries
185. ICML 2026Trust Functions: Near Lossless Weak-to-Strong Generalization by Learning to Trust the Weak Teacher
186. ICML 2026Trustworthy Federated Label Distribution Learning under Annotation Quality Disparity
187. ICML 2026Tuning-Free One-Class Discriminant Learning for Tabular Anomaly Detection
188. ICML 2026Two-Layer Linear Auto-Regressive Models Estimate Latent States
189. ICML 2026Uncovering the Gradient Geometry of Long CoT: A Spectral-guided Approach to Reasoning Distillation
190. ICML 2026Understanding Self-Supervised Learning via Latent Distribution Matching
191. ICML 2026When More Experts Hurt: Underfitting in Multi-Expert Learning to Defer
192. NeurIPS 2026AOT-POT: Adaptive Operator Transformation for Large-Scale PDE Pre-training
193. NeurIPS 2026Approximation of Maximally Monotone Operators : A Graph Convergence Perspective
194. NeurIPS 2026Are Well-Trained Surrogates Optimal? Rethinking the Surrogate Role with Instability for Unlearnable Examples
195. NeurIPS 2026AudioSphere: Towards Self-Supervised Spatial Audio Representation Models
196. NeurIPS 2026Auditing Single-Query Recoverability in Self-Supervised Representations
197. NeurIPS 2026BayesAT: Bayes-Guided Progressive Distillation for Semi-Supervised Adversarial Training
198. NeurIPS 2026Capturing Membrane Dynamics and Spike Timing of Human Neurons at Scale using Neural Operators
199. NeurIPS 2026Claudini: Autoresearch Discovers State-of-the-Art Adversarial Attack Algorithms for LLMs
200. NeurIPS 2026CLEAR: Complementary Tripartite Play with Bayesian Calibration for Semi-Supervised Edge Classification

常见问题

2023–2026 年四大会议一共有多少篇通用机器学习 · supervised learning论文？

共 1,425 篇，按年份分别是 2023 年 263 篇、2024 年 511 篇、2025 年 372 篇、2026 年 279 篇。

NeurIPS 2026 有多少篇通用机器学习 · supervised learning论文？

NeurIPS 2026 有 87 篇通用机器学习 · supervised learning论文，上一届是 171 篇。

ICLR 2026 有多少篇通用机器学习 · supervised learning论文？

ICLR 2026 有 48 篇通用机器学习 · supervised learning论文，上一届是 40 篇。

ICML 2026 有多少篇通用机器学习 · supervised learning论文？

ICML 2026 有 111 篇通用机器学习 · supervised learning论文，上一届是 114 篇。

CVPR 2026 有多少篇通用机器学习 · supervised learning论文？

CVPR 2026 有 33 篇通用机器学习 · supervised learning论文，上一届是 47 篇。

哪个会议的通用机器学习 · supervised learning论文最多？

NeurIPS，2023–2026 年共 731 篇。