自适应方法论文趋势 2023–2026

主要结论

• 自适应方法论文从 2023 年的 143 篇增长到 2026 年的 410 篇，三年间扩大到约 2.9 倍。
• NeurIPS 是发自适应方法论文最多的会议，2023–2026 年共 365 篇，占四个会议总量的 36%。
• 交叉方向里涨得最快的是理论 · optimization：同时属于两个主题的论文从 2023 年的 1 篇增至 2026 年的 29 篇。
• 在「优化与缩放」的 5 个主题里，它的 2026 年论文数排第 3；同组增长最快的缩放定律是 4.1 倍，自适应方法是 2.9 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 2026AcceleGrad#: Adaptive Geometry-Aware Acceleration
• ICML 2026Adaptive Bandit Algorithms for Contextual Matching Markets
• ICLR 2026Adaptive Width Neural Networks
• CVPR 2026Active Inference for Micro-Gesture Recognition EFE-Guided Temporal Sampling and Adaptive
• NeurIPS 2025AC-DiT: Adaptive Coordination Diffusion Transformer for Mobile Manipulation
• ICML 2025Adaptive Data Collection for Robust Learning Across Multiple Distributions
• ICLR 2025Adaptive Length Image Tokenization via Recurrent Allocation
• CVPR 2025A Universal Scale-Adaptive Deformable Transformer for Image Restoration across Diverse Artifacts
• NeurIPS 2024Semi-Discrete Optimal Transport: Nearly Minimax Estimation With Stochastic Gradient Descent and Adaptive Entropic Regularization
• ICML 2024A New Linear Scaling Rule for Private Adaptive Hyperparameter Optimization
• ICLR 2024Learning Adaptive Multiresolution Transforms via Meta-Framelet-based Graph Convolutional Network
• CVPR 2024HybridNeRF: Efficient Neural Rendering via Adaptive Volumetric Surfaces
• NeurIPS 2023A Bounded Ability Estimation for Computerized Adaptive Testing
• ICML 2023A/B Testing in Network Data with Covariate-Adaptive Randomization
• ICLR 2023An Adaptive Policy to Employ Sharpness-Aware Minimization
• CVPR 2023Adaptive Annealing for Robust Geometric Estimation
• NeurIPS 2026AdapMatch: Adaptive Bias Decoupling for Semi-Supervised Partial Label Learning under Unknown Class Distributions
• ICML 2026Adaptive Batch Sizes Using Non-Euclidean Gradient Noise Scales for Stochastic Sign and Spectral Descent
• ICLR 2026ARMOR: High-Performance Semi-Structured Pruning via Adaptive Matrix Factorization
• CVPR 2026Adaptive Learned Image Compression with Graph Neural Networks

全部自适应方法论文

共 183 篇，第 3 / 4 页

101. ICML 2024MADA: Meta-Adaptive Optimizers Through Hyper-Gradient Descent
102. ICML 2024MoMo: Momentum Models for Adaptive Learning Rates
103. ICML 2024Multi-Factor Adaptive Vision Selection for Egocentric Video Question Answering
104. ICML 2024Navigating Scaling Laws: Compute Optimality in Adaptive Model Training
105. ICML 2024Neurodegenerative Brain Network Classification via Adaptive Diffusion with Temporal Regularization
106. ICML 2024On Gradient-like Explanation under a Black-box Setting: When Black-box Explanations Become as Good as White-box
107. ICML 2024On the Implicit Bias of Adam
108. ICML 2024One Size Fits All for Semantic Shifts: Adaptive Prompt Tuning for Continual Learning
109. ICML 2024Online Adaptive Anomaly Thresholding with Confidence Sequences
110. ICML 2024Overcoming the Optimizer's Curse: Obtaining Realistic Prescriptions from Neural Networks
111. ICML 2024PASOA- PArticle baSed Bayesian Optimal Adaptive design
112. ICML 2024PriorBoost: An Adaptive Algorithm for Learning from Aggregate Responses
113. ICML 2024Privacy Preserving Adaptive Experiment Design
114. ICML 2024Prodigy: An Expeditiously Adaptive Parameter-Free Learner
115. ICML 2024RODEO: Robust Outlier Detection via Exposing Adaptive Out-of-Distribution Samples
116. ICML 2024Small-loss Adaptive Regret for Online Convex Optimization
117. ICML 2024Smoothness Adaptive Hypothesis Transfer Learning
118. ICML 2024Studying K-FAC Heuristics by Viewing Adam through a Second-Order Lens
119. ICML 2024Unmasking Vulnerabilities: Cardinality Sketches under Adaptive Inputs
120. NeurIPS 2024A PID Controller Approach for Adaptive Probability-dependent Gradient Decay in Model Calibration
121. NeurIPS 2024Ada-MSHyper: Adaptive Multi-Scale Hypergraph Transformer for Time Series Forecasting
122. NeurIPS 2024AdaFlow: Imitation Learning with Variance-Adaptive Flow-Based Policies
123. NeurIPS 2024Adaptive $Q$-Aid for Conditional Supervised Learning in Offline Reinforcement Learning
124. NeurIPS 2024Adaptive and Optimal Second-order Optimistic Methods for Minimax Optimization
125. NeurIPS 2024Adaptive Depth Networks with Skippable Sub-Paths
126. NeurIPS 2024Adaptive Experimentation When You Can't Experiment
127. NeurIPS 2024Adaptive Important Region Selection with Reinforced Hierarchical Search for Dense Object Detection
128. NeurIPS 2024Adaptive Layer Sparsity for Large Language Models via Activation Correlation Assessment
129. NeurIPS 2024Adaptive Passive-Aggressive Framework for Online Regression with Side Information
130. NeurIPS 2024Adaptive Preference Scaling for Reinforcement Learning with Human Feedback
131. NeurIPS 2024Adaptive Proximal Gradient Method for Convex Optimization
132. NeurIPS 2024Adaptive Sampling for Efficient Softmax Approximation
133. NeurIPS 2024Adaptive Variance Reduction for Stochastic Optimization under Weaker Assumptions
134. NeurIPS 2024ADOPT: Modified Adam Can Converge with Any $\beta_2$ with the Optimal Rate
135. NeurIPS 2024An Adaptive Approach for Infinitely Many-armed Bandits under Generalized Rotting Constraints
136. NeurIPS 2024ANT: Adaptive Noise Schedule for Time Series Diffusion Models
137. NeurIPS 2024Boosting Generalization in Parametric PDE Neural Solvers through Adaptive Conditioning
138. NeurIPS 2024CLAVE: An Adaptive Framework for Evaluating Values of LLM Generated Responses
139. NeurIPS 2024Cluster-Learngene: Inheriting Adaptive Clusters for Vision Transformers
140. NeurIPS 2024Clustering with Non-adaptive Subset Queries
141. NeurIPS 2024CoMERA: Computing- and Memory-Efficient Training via Rank-Adaptive Tensor Optimization
142. NeurIPS 2024Computerized Adaptive Testing via Collaborative Ranking
143. NeurIPS 2024Constrained Adaptive Attack: Effective Adversarial Attack Against Deep Neural Networks for Tabular Data
144. NeurIPS 2024D-LLM: A Token Adaptive Computing Resource Allocation Strategy for Large Language Models
145. NeurIPS 2024DAPE: Data-Adaptive Positional Encoding for Length Extrapolation
146. NeurIPS 2024DARG: Dynamic Evaluation of Large Language Models via Adaptive Reasoning Graph
147. NeurIPS 2024DHA: Learning Decoupled-Head Attention from Transformer Checkpoints via Adaptive Heads Fusion
148. NeurIPS 2024Diffusion Models With Learned Adaptive Noise
149. NeurIPS 2024DiGRAF: Diffeomorphic Graph-Adaptive Activation Function
150. NeurIPS 2024Dynamic Subgroup Identification in Covariate-adjusted Response-adaptive Randomization Experiments

常见问题

2023–2026 年四大会议一共有多少篇自适应方法论文？

共 1,012 篇，按年份分别是 2023 年 143 篇、2024 年 183 篇、2025 年 276 篇、2026 年 410 篇。

NeurIPS 2026 有多少篇自适应方法论文？

NeurIPS 2026 有 138 篇自适应方法论文，上一届是 109 篇。

ICLR 2026 有多少篇自适应方法论文？

ICLR 2026 有 80 篇自适应方法论文，上一届是 47 篇。

ICML 2026 有多少篇自适应方法论文？

ICML 2026 有 109 篇自适应方法论文，上一届是 68 篇。

CVPR 2026 有多少篇自适应方法论文？

CVPR 2026 有 83 篇自适应方法论文，上一届是 52 篇。

哪个会议的自适应方法论文最多？

NeurIPS，2023–2026 年共 365 篇。