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 143 篇，第 2 / 3 页

51. ICLR 2023Diffusion-GAN: Training GANs with Diffusion
52. ICLR 2023Distributed Extra-gradient with Optimal Complexity and Communication Guarantees
53. ICLR 2023DySR: Adaptive Super-Resolution via Algorithm and System Co-design
54. ICLR 2023Fast and Precise: Adjusting Planning Horizon with Adaptive Subgoal Search
55. ICLR 2023FreeMatch: Self-adaptive Thresholding for Semi-supervised Learning
56. ICLR 2023Imbalanced Semi-supervised Learning with Bias Adaptive Classifier
57. ICLR 2023Is Adversarial Training Really a Silver Bullet for Mitigating Data Poisoning?
58. ICLR 2023MaskFusion: Feature Augmentation for Click-Through Rate Prediction via Input-adaptive Mask Fusion
59. ICLR 2023Maximizing Communication Efficiency for Large-scale Training via 0/1 Adam
60. ICLR 2023Neural ePDOs: Spatially Adaptive Equivariant Partial Differential Operator Based Networks
61. ICLR 2023Noise Is Not the Main Factor Behind the Gap Between Sgd and Adam on Transformers, But Sign Descent Might Be
62. ICLR 2023Pruning Deep Neural Networks from a Sparsity Perspective
63. ICLR 2023Robust Algorithms on Adaptive Inputs from Bounded Adversaries
64. ICLR 2023SP2 : A Second Order Stochastic Polyak Method
65. ICLR 2023TiAda: A Time-scale Adaptive Algorithm for Nonconvex Minimax Optimization
66. ICLR 2023When to Make and Break Commitments?
67. ICLR 2023Win: Weight-Decay-Integrated Nesterov Acceleration for Adaptive Gradient Algorithms
68. ICML 2023A/B Testing in Network Data with Covariate-Adaptive Randomization
69. ICML 2023Adaptive Annealed Importance Sampling with Constant Rate Progress
70. ICML 2023Adaptive Compositional Continual Meta-Learning
71. ICML 2023Adaptive Computation with Elastic Input Sequence
72. ICML 2023Adaptive Coordination in Social Embodied Rearrangement
73. ICML 2023Adaptive Estimation of Graphical Models under Total Positivity
74. ICML 2023Adaptive IMLE for Few-shot Pretraining-free Generative Modelling
75. ICML 2023Adaptive Whitening in Neural Populations with Gain-modulating Interneurons
76. ICML 2023Addressing Budget Allocation and Revenue Allocation in Data Market Environments Using an Adaptive Sampling Algorithm
77. ICML 2023Bidirectional Looking with A Novel Double Exponential Moving Average to Adaptive and Non-adaptive Momentum Optimizers
78. ICML 2023Emergence of Adaptive Circadian Rhythms in Deep Reinforcement Learning
79. ICML 2023Facial Expression Recognition with Adaptive Frame Rate based on Multiple Testing Correction
80. ICML 2023Fully-Adaptive Composition in Differential Privacy
81. ICML 2023Improved Online Conformal Prediction via Strongly Adaptive Online Learning
82. ICML 2023Learning Rate Schedules in the Presence of Distribution Shift
83. ICML 2023LipsNet: A Smooth and Robust Neural Network with Adaptive Lipschitz Constant for High Accuracy Optimal Control
84. ICML 2023Lookahead When It Matters: Adaptive Non-causal Transformers for Streaming Neural Transducers
85. ICML 2023Non-asymptotic Properties of Individualized Treatment Rules from Sequentially Rule-Adaptive Trials
86. ICML 2023On the Convergence Rates of Policy Gradient Methods
87. ICML 2023Shedding a PAC-Bayesian Light on Adaptive Sliced-Wasserstein Distances
88. ICML 2023Theoretical Behavior of XAI Methods in the Presence of Suppressor Variables
89. ICML 2023Uncertainty Estimation for Molecules: Desiderata and Methods
90. NeurIPS 2023[Re] Hierarchical Shrinkage: Improving the Accuracy and Interpretability of Tree-Based Methods
91. NeurIPS 2023A Bounded Ability Estimation for Computerized Adaptive Testing
92. NeurIPS 2023AdANNS: A Framework for Adaptive Semantic Search
93. NeurIPS 2023AdaPlanner: Adaptive Planning from Feedback with Language Models
94. NeurIPS 2023Adaptive Algorithms for Relaxed Pareto Set Identification
95. NeurIPS 2023Adaptive Contextual Perception: How To Generalize To New Backgrounds and Ambiguous Objects
96. NeurIPS 2023Adaptive Linear Estimating Equations
97. NeurIPS 2023Adaptive Online Replanning with Diffusion Models
98. NeurIPS 2023Adaptive Privacy Composition for Accuracy-first Mechanisms
99. NeurIPS 2023Adaptive SGD with Polyak stepsize and Line-search: Robust Convergence and Variance Reduction
100. NeurIPS 2023Adaptive Test-Time Personalization for Federated Learning

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。