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 109 篇，第 2 / 3 页

51. ICML 2026DropoutTS: Sample-Adaptive Dropout for Robust Time Series Forecasting
52. ICML 2026Dual-channel Dynamic Graph Neural Networks with Adaptive Adjacency Learning and Multi-scale Representation Fusion
53. ICML 2026DuetServe: Harmonizing Prefill and Decode for LLM Serving via Adaptive GPU Multiplexing
54. ICML 2026Entropic Mirror Monte Carlo
55. ICML 2026Entropy-informed Decoding: Adaptive Information-Driven Branching
56. ICML 2026FedVeer: Self-Adaptive Skew Estimation for Robust Federated Learning
57. ICML 2026FOAM: Frequency and Operator-Error Based Adaptive Damping Method for Reducing Staleness-Oriented Error for Shampoo
58. ICML 2026Geometric Convergence of Gauss–Newton for Neural Networks: Riemannian Geometry and Adaptive Damping
59. ICML 2026Geometry-Misalignment in Distributional Learning
60. ICML 2026Global Convergence of Adaptive Sensing for Principal Eigenvector Estimation
61. ICML 2026GP2F: Cross-Domain Graph Prompting with Adaptive Fusion of Pre-trained Graph Neural Networks
62. ICML 2026GradientStabilizer: Fix the Norm, Not the Gradient
63. ICML 2026HARD-KV: Head-Adaptive Regularization for Decoding-time KV Compression
64. ICML 2026HybridFlow: Resource-Adaptive Subtask Routing for Efficient Edge-Cloud LLM Inference
65. ICML 2026Identifiable Nonlinear Differentiable Causal Discovery via Independence and Adaptive Group Sparsity
66. ICML 2026IO-Adam: Rethinking Memory-Efficient Adaptive Optimizers from Gradient Computation
67. ICML 2026JADAI: Jointly Amortizing Adaptive Design and Bayesian Inference
68. ICML 2026KnapSpec: Self-Speculative Decoding via Adaptive Layer Selection as a Knapsack Problem
69. ICML 2026LDARNet: DNA Adaptive Representation Network with Learnable Tokenization for Genomic Modeling
70. ICML 2026Learning Adaptive Perturbation-Conditioned Contexts for Robust Transcriptional Response Prediction
71. ICML 2026Learning Adaptive Topology with FiLM-Guided Distillation for Tertiary Structure-Based RNA Design
72. ICML 2026LoRe: Adaptive Interaction-Evaluation Routing with Per-step Interaction Budgets for Iterative Graph Solvers
73. ICML 2026M+Adam: Low-Precision Training via Additive–Multiplicative Optimization
74. ICML 2026Margin-Adaptive Confidence Ranking for Reliable LLM Judgement
75. ICML 2026MedMamba: Multi-View State Space Models with Adaptive Graph Learning for Medical Time Series Classification
76. ICML 2026MixFP4: Enhancing NVFP4 with Adaptive FP4/INT4 Block Representations
77. ICML 2026Model-Preserving Adaptive Rounding
78. ICML 2026Multi-Objective Bayesian Optimization via Adaptive $\varepsilon$-Constraint Decomposition
79. ICML 2026Navigating the Flatlands: Dual Adaptive Sharpness-Aware Minimization for Domain Generalization
80. ICML 2026Neural Attention Search Linear: Towards Adaptive Token-Level Hybrid Attention Models
81. ICML 2026Not All Frequencies Are Equal: Energy-Adaptive Diffusion for Time Series Forecasting
82. ICML 2026OmniFit: Bridging Modalities via Layer-Adaptive Token Compression for Omnimodal Large Language Models
83. ICML 2026PACEAttention: Principled and Adaptive Feature Compression-Expansion Grounded in the Geometry of $\text{MCR}^2$
84. ICML 2026PAMD: Structured Adaptive Distances for Bisimulation Representations in Visual Reinforcement Learning
85. ICML 2026Preconditioning Neural Tangent Kernel for Adaptive Optimization
86. ICML 2026Prediction-Powered Adaptive Inference with Pretrained AI Models for Contextual Bandits
87. ICML 2026PRISM: Distribution-free Adaptive Computation of Matrix Functions for Accelerating Neural Network Training
88. ICML 2026QTALE: Quantization-Robust Token-Adaptive Layer Execution for LLMs
89. ICML 2026Randomized Feasibility Methods for Constrained Optimization with Adaptive Step Sizes
90. ICML 2026Reasoning as an Attack Surface: Adaptive Evolutionary CoT Jailbreaks for LLMs
91. ICML 2026Regime-Adaptive Bayesian Optimization via Dirichlet Process Mixtures of Gaussian Processes
92. ICML 2026Retriever Portfolios: A Principled Approach to Adaptive RAG
93. ICML 2026Robust Federated Learning Against Adaptive Compression
94. ICML 2026SAQNN: Spectral Adaptive Quantum Neural Network as a Universal Approximator
95. ICML 2026Scalable Reinforcement Learning via Adaptive Batch Scaling
96. ICML 2026Sequential Kernel-based Conditional Independence Testing via Adaptive Betting
97. ICML 2026SFCLTA: Spectral Fusion Contrastive Learning with Topology-Adaptive Graph Augmentation
98. ICML 2026Singular Proxies for Adaptive Caching in Diffusion Language Models
99. ICML 2026Spatially-Adaptive Gradient Re-parameterization for 3D Large Kernel Optimization
100. ICML 2026StretchTime: Adaptive Time Series Forecasting via Symplectic Attention

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。