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 3 / 4 页

101. ICLR 2025Convergence of Distributed Adaptive Optimization with Local Updates
102. ICLR 2025CoTFormer: A Chain of Thought Driven Architecture with Budget-Adaptive Computation Cost at Inference
103. ICLR 2025Data-adaptive Differentially Private Prompt Synthesis for In-Context Learning
104. ICLR 2025DenoiseVAE: Learning Molecule-Adaptive Noise Distributions for Denoising-based 3D Molecular Pre-training
105. ICLR 2025Dynamic Neural Fortresses: An Adaptive Shield for Model Extraction Defense
106. ICLR 2025Ensembling Diffusion Models via Adaptive Feature Aggregation
107. ICLR 2025Faster Cascades via Speculative Decoding
108. ICLR 2025FedLWS: Federated Learning with Adaptive Layer-wise Weight Shrinking
109. ICLR 2025From Attention to Activation: Unraveling the Enigmas of Large Language Models
110. ICLR 2025From Decoupling to Adaptive Transformation: a Wider Optimization Space for PTQ
111. ICLR 2025InstaTrain: Adaptive Training via Ultra-Fast Natural Annealing within Dynamical Systems
112. ICLR 2025Learning How Hard to Think: Input-Adaptive Allocation of LM Computation
113. ICLR 2025MatryoshkaKV: Adaptive KV Compression via Trainable Orthogonal Projection
114. ICLR 2025MIND over Body: Adaptive Thinking using Dynamic Computation
115. ICLR 2025Neural ODE Transformers: Analyzing Internal Dynamics and Adaptive Fine-tuning
116. ICLR 2025NExUME: Adaptive Training and Inference for DNNs under Intermittent Power Environments
117. ICLR 2025PEARL: Parallel Speculative Decoding with Adaptive Draft Length
118. ICLR 2025PIG: Physics-Informed Gaussians as Adaptive Parametric Mesh Representations
119. ICLR 2025Refine Knowledge of Large Language Models via Adaptive Contrastive Learning
120. ICLR 2025Revisit Micro-batch Clipping: Adaptive Data Pruning via Gradient Manipulation
121. ICLR 2025Scalable Universal T-Cell Receptor Embeddings from Adaptive Immune Repertoires
122. ICLR 2025SparsyFed: Sparse Adaptive Federated Learning
123. ICLR 2025Swift4D: Adaptive divide-and-conquer Gaussian Splatting for compact and efficient reconstruction of dynamic scene
124. ICLR 2025TAID: Temporally Adaptive Interpolated Distillation for Efficient Knowledge Transfer in Language Models
125. ICLR 2025Towards a General Time Series Anomaly Detector with Adaptive Bottlenecks and Dual Adversarial Decoders
126. ICLR 2025Towards Domain Adaptive Neural Contextual Bandits
127. ICLR 2025Towards Generalizable Reinforcement Learning via Causality-Guided Self-Adaptive Representations
128. ICLR 2024AdaMerging: Adaptive Model Merging for Multi-Task Learning
129. ICLR 2024Adaptive Chameleon or Stubborn Sloth: Revealing the Behavior of Large Language Models in Knowledge Conflicts
130. ICLR 2024Adaptive Federated Learning with Auto-Tuned Clients
131. ICLR 2024Adaptive Instrument Design for Indirect Experiments
132. ICLR 2024Adaptive Rational Activations to Boost Deep Reinforcement Learning
133. ICLR 2024Adaptive Regret for Bandits Made Possible: Two Queries Suffice
134. ICLR 2024Adaptive Window Pruning for Efficient Local Motion Deblurring
135. ICLR 2024Adversarial Adaptive Sampling: Unify PINN and Optimal Transport for the Approximation of PDEs
136. ICLR 2024ARM: Refining Multivariate Forecasting with Adaptive Temporal-Contextual Learning
137. ICLR 2024Beyond Worst-case Attacks: Robust RL with Adaptive Defense via Non-dominated Policies
138. ICLR 2024Chameleon: Increasing Label-Only Membership Leakage with Adaptive Poisoning
139. ICLR 2024Efficient Backpropagation with Variance Controlled Adaptive Sampling
140. ICLR 2024FedDA: Faster Adaptive Gradient Methods for Federated Constrained Optimization
141. ICLR 2024Generalization in diffusion models arises from geometry-adaptive harmonic representations
142. ICLR 2024Implicit Maximum a Posteriori Filtering via Adaptive Optimization
143. ICLR 2024Learning Adaptive Multiresolution Transforms via Meta-Framelet-based Graph Convolutional Network
144. ICLR 2024Only Pay for What Is Uncertain: Variance-Adaptive Thompson Sampling
145. ICLR 2024Pathformer: Multi-scale Transformers with Adaptive Pathways for Time Series Forecasting
146. ICLR 2024SAFLEX: Self-Adaptive Augmentation via Feature Label Extrapolation
147. ICLR 2024Scalable Modular Network: A Framework for Adaptive Learning via Agreement Routing
148. ICLR 2024Scale-Adaptive Diffusion Model for Complex Sketch Synthesis
149. ICLR 2024Towards Green AI in Fine-tuning Large Language Models via Adaptive Backpropagation
150. ICLR 2023Adaptive Budget Allocation for Parameter-Efficient Fine-Tuning

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。