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 410 篇，第 3 / 9 页

101. ICLR 2026Adaptive Scaling of Policy Constraints for Offline Reinforcement Learning
102. ICLR 2026Adaptive Thinking: Large Language Models Know When to Think in Latent Space
103. ICLR 2026Adaptive Width Neural Networks
104. ICLR 2026AdaRank: Adaptive Rank Pruning for Enhanced Model Merging
105. ICLR 2026AdaSpec: Adaptive Spectrum for Enhanced Node Distinguishability
106. ICLR 2026ADEPT: Continual Pretraining via Adaptive Expansion and Dynamic Decoupled Tuning
107. ICLR 2026AFTER: Mitigating the Object Hallucination of LVLM via Adaptive Factual-Guided Activation Editing
108. ICLR 2026APC-RL: Exceeding data-driven behavior priors with adaptive policy composition
109. ICLR 2026ARMOR: High-Performance Semi-Structured Pruning via Adaptive Matrix Factorization
110. ICLR 2026ASTGI: Adaptive Spatio-Temporal Graph Interactions for Irregular Multivariate Time Series Forecasting
111. ICLR 2026Automated Stateful Specialization for Adaptive Agent Systems
112. ICLR 2026ByteFlow: Language Modeling through Adaptive Byte Compression without a Tokenizer
113. ICLR 2026Code Driven Planning with Domain-Adaptive Selector
114. ICLR 2026CooperTrim: Adaptive Data Selection for Uncertainty-Aware Cooperative Perception
115. ICLR 2026COSMOS: A Hybrid Adaptive Optimizer for Efficient Training of Large Language Models
116. ICLR 2026d$^2$Cache: Accelerating Diffusion-Based LLMs via Dual Adaptive Caching
117. ICLR 2026Deep Hierarchical Learning with Nested Subspace Networks
118. ICLR 2026DES-LOC: Desynced Low Communication Adaptive Optimizers for Foundation Models
119. ICLR 2026Dynamic-dLLM: Dynamic Cache-Budget and Adaptive Parallel Decoding for Training-Free Acceleration of Diffusion LLM
120. ICLR 2026E²LoRA: Efficient and Effective Low-Rank Adaptation with Entropy-Guided Adaptive Sharing
121. ICLR 2026Expressive yet Efficient Feature Expansion with Adaptive Cross-Hadamard Products
122. ICLR 2026Fairness-Aware Multi-view Evidential Learning with Adaptive Prior
123. ICLR 2026Fast Frank–Wolfe Algorithms with Adaptive Bregman Step-Size for Weakly Convex Functions
124. ICLR 2026FutureMind: Equipping Small Language Models with Strategic Thinking-Pattern Priors via Adaptive Knowledge Distillation
125. ICLR 2026FZOO: Fast Zeroth-Order Optimizer for Fine‑Tuning Large Language Models towards Adam‑Scale Speed
126. ICLR 2026Graph Signal Processing Meets Mamba2: Adaptive Filter Bank via Delta Modulation
127. ICLR 2026High-dimensional limit theorems for SGD: Momentum and Adaptive Step-sizes
128. ICLR 2026Implicit Bias of Per-sample Adam on Separable Data: Departure from the Full-batch Regime
129. ICLR 2026Instance-wise Adaptive Scheduling via Derivative-Free Meta-Learning
130. ICLR 2026JAPAN: Joint Adaptive Prediction Areas with Normalising Flow
131. ICLR 2026Learn to Reason Efficiently with Adaptive Length-based Reward Shaping
132. ICLR 2026Learning To Draft: Adaptive Speculative Decoding with Reinforcement Learning
133. ICLR 2026Learning to Parallel: Accelerating Diffusion Large Language Models via Adaptive Parallel Decoding
134. ICLR 2026LogART: Pushing the Limit of Efficient Logarithmic Post-Training Quantization
135. ICLR 2026Look Carefully: Adaptive Visual Reinforcements in Multimodal Large Language Models for Hallucination Mitigation
136. ICLR 2026MambaSL: Exploring Single-Layer Mamba for Time Series Classification
137. ICLR 2026MaRS: Memory-Adaptive Routing for Reliable Capacity Expansion and Knowledge Retention
138. ICLR 2026MIRACLE: Model-free Imitation and Reinforcement Learning for Adaptive Cut-Selection
139. ICLR 2026Multi-LLM Adaptive Conformal Inference for Reliable LLM Response
140. ICLR 2026NAB: Neural Adaptive Binning for Sparse-View CT reconstruction
141. ICLR 2026Native Adaptive Solution Expansion for Diffusion-based Combinatorial Optimization
142. ICLR 2026Nesterov Finds GRAAL: Optimal and Adaptive Gradient Method for Convex Optimization
143. ICLR 2026Noise-Adaptive Diffusion Sampling for Inverse Problems Without Task-Specific Tuning
144. ICLR 2026Offline Reinforcement Learning with Adaptive Feature Fusion
145. ICLR 2026Optimizer Choice Matters For The Emergence of Neural Collapse
146. ICLR 2026Overlap-Adaptive Regularization for Conditional Average Treatment Effect Estimation
147. ICLR 2026Robust Equation Structure learning with Adaptive Refinement
148. ICLR 2026SAES-SVD: Self-Adaptive Suppression of Accumulated and Local Errors for SVD-based LLM Compression
149. ICLR 2026Scalable and Adaptive Trust-Region Learning via Projection Convex Hull
150. ICLR 2026SDErasure: Concept-Specific Trajectory Shifting for Concept Erasure via Adaptive Diffusion Classifier

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。