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 173 篇，第 2 / 4 页

51. ICLR 2026LogART: Pushing the Limit of Efficient Logarithmic Post-Training Quantization
52. ICLR 2026Look Carefully: Adaptive Visual Reinforcements in Multimodal Large Language Models for Hallucination Mitigation
53. ICLR 2026MambaSL: Exploring Single-Layer Mamba for Time Series Classification
54. ICLR 2026MaRS: Memory-Adaptive Routing for Reliable Capacity Expansion and Knowledge Retention
55. ICLR 2026MIRACLE: Model-free Imitation and Reinforcement Learning for Adaptive Cut-Selection
56. ICLR 2026Multi-LLM Adaptive Conformal Inference for Reliable LLM Response
57. ICLR 2026NAB: Neural Adaptive Binning for Sparse-View CT reconstruction
58. ICLR 2026Native Adaptive Solution Expansion for Diffusion-based Combinatorial Optimization
59. ICLR 2026Nesterov Finds GRAAL: Optimal and Adaptive Gradient Method for Convex Optimization
60. ICLR 2026Noise-Adaptive Diffusion Sampling for Inverse Problems Without Task-Specific Tuning
61. ICLR 2026Offline Reinforcement Learning with Adaptive Feature Fusion
62. ICLR 2026Optimizer Choice Matters For The Emergence of Neural Collapse
63. ICLR 2026Overlap-Adaptive Regularization for Conditional Average Treatment Effect Estimation
64. ICLR 2026Robust Equation Structure learning with Adaptive Refinement
65. ICLR 2026SAES-SVD: Self-Adaptive Suppression of Accumulated and Local Errors for SVD-based LLM Compression
66. ICLR 2026Scalable and Adaptive Trust-Region Learning via Projection Convex Hull
67. ICLR 2026SDErasure: Concept-Specific Trajectory Shifting for Concept Erasure via Adaptive Diffusion Classifier
68. ICLR 2026SGD with Adaptive Preconditioning: Unified Analysis and Momentum Acceleration
69. ICLR 2026Softmax is not Enough (for Adaptive Conformal Classification)
70. ICLR 2026SONATA: Synergistic Coreset Informed Adaptive Temporal Tensor Factorization
71. ICLR 2026SPREAD: Sampling-based Pareto front Refinement via Efficient Adaptive Diffusion
72. ICLR 2026Stabilizing Off-Policy Reinforcement Learning for LLMs via Balanced Policy Optimization with Adaptive Clipping
73. ICLR 2026STAT: Skill-Targeted Adaptive Training
74. ICLR 2026Sysformer: Safeguarding Frozen Large Language Models with Adaptive System Prompts
75. ICLR 2026Tackling the XAI Disagreement Problem with Adaptive Feature Grouping
76. ICLR 2026Task-free Adaptive Meta Black-box Optimization
77. ICLR 2026Temperature as a Meta-Policy: Adaptive Temperature in LLM Reinforcement Learning
78. ICLR 2026ThinKV: Thought-Adaptive KV Cache Compression for Efficient Reasoning Models
79. ICLR 2026Trust but Verify: Adaptive Conditioning for Reference-Based Diffusion Super-Resolution via Implicit Reference Correlation Modeling
80. ICLR 2026UniQL: Unified Quantization and Low-rank Compression for Adaptive Edge LLMs
81. ICLR 2025AdaFisher: Adaptive Second Order Optimization via Fisher Information
82. ICLR 2025AdaGrad under Anisotropic Smoothness
83. ICLR 2025Adam Exploits $\ell_\infty$-geometry of Loss Landscape via Coordinate-wise Adaptivity
84. ICLR 2025ADAM Optimization with Adaptive Batch Selection
85. ICLR 2025Adaptive $Q$-Network: On-the-fly Target Selection for Deep Reinforcement Learning
86. ICLR 2025Adaptive backtracking line search
87. ICLR 2025Adaptive Batch Size for Privately Finding Second-Order Stationary Points
88. ICLR 2025Adaptive Length Image Tokenization via Recurrent Allocation
89. ICLR 2025Adaptive Methods through the Lens of SDEs: Theoretical Insights on the Role of Noise
90. ICLR 2025Adaptive Pruning of Pretrained Transformer via Differential Inclusions
91. ICLR 2025Adaptive Rank Allocation: Speeding Up Modern Transformers with RaNA Adapters
92. ICLR 2025Adaptive Shrinkage Estimation for Personalized Deep Kernel Regression in Modeling Brain Trajectories
93. ICLR 2025Adaptive teachers for amortized samplers
94. ICLR 2025Adaptive Transformer Programs: Bridging the Gap Between Performance and Interpretability in Transformers
95. ICLR 2025ASTrA: Adversarial Self-supervised Training with Adaptive-Attacks
96. ICLR 2025Breaking the $\log(1/\Delta_2)$ Barrier: Better Batched Best Arm Identification with Adaptive Grids
97. ICLR 2025Budgeted Online Continual Learning by Adaptive Layer Freezing and Frequency-based Sampling
98. ICLR 2025CAKE: Cascading and Adaptive KV Cache Eviction with Layer Preferences
99. ICLR 2025Complexity Lower Bounds of Adaptive Gradient Algorithms for Non-convex Stochastic Optimization under Relaxed Smoothness
100. ICLR 2025CONDA: Adaptive Concept Bottleneck for Foundation Models Under Distribution Shifts

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。