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 68 篇，第 1 / 2 页

1. ICML 2025A Comprehensive Framework for Analyzing the Convergence of Adam: Bridging the Gap with SGD
2. ICML 2025AdaDecode: Accelerating LLM Decoding with Adaptive Layer Parallelism
3. ICML 2025Adaptive Data Collection for Robust Learning Across Multiple Distributions
4. ICML 2025Adaptive Estimation and Learning under Temporal Distribution Shift
5. ICML 2025Adaptive Exploration for Multi-Reward Multi-Policy Evaluation
6. ICML 2025Adaptive Flow Matching for Resolving Small-Scale Physics
7. ICML 2025Adaptive kernel predictors from feature-learning infinite limits of neural networks
8. ICML 2025Adaptive Learn-then-Test: Statistically Valid and Efficient Hyperparameter Selection
9. ICML 2025Adaptive Localization of Knowledge Negation for Continual LLM Unlearning
10. ICML 2025Adaptive Message Passing: A General Framework to Mitigate Oversmoothing, Oversquashing, and Underreaching
11. ICML 2025Adaptive Partitioning Schemes for Optimistic Optimization
12. ICML 2025Adaptive Sample Sharing for Multi Agent Linear Bandits
13. ICML 2025Adaptive Self-improvement LLM Agentic System for ML Library Development
14. ICML 2025AdaSplash: Adaptive Sparse Flash Attention
15. ICML 2025ADDQ: Adaptive distributional double Q-learning
16. ICML 2025AKORN: Adaptive Knots generated Online for RegressioN splines
17. ICML 2025AKRMap: Adaptive Kernel Regression for Trustworthy Visualization of Cross-Modal Embeddings
18. ICML 2025An Adaptive Orthogonal Convolution Scheme for Efficient and Flexible CNN Architectures
19. ICML 2025An Expressive and Self-Adaptive Dynamical System for Efficient Function Learning
20. ICML 2025An Online Adaptive Sampling Algorithm for Stochastic Difference-of-convex Optimization with Time-varying Distributions
21. ICML 2025AutoGFM: Automated Graph Foundation Model with Adaptive Architecture Customization
22. ICML 2025AutoStep: Locally adaptive involutive MCMC
23. ICML 2025Balancing Model Efficiency and Performance: Adaptive Pruner for Long-tailed Data
24. ICML 2025BanditSpec: Adaptive Speculative Decoding via Bandit Algorithms
25. ICML 2025BECAME: Bayesian Continual Learning with Adaptive Model Merging
26. ICML 2025Beyond Matryoshka: Revisiting Sparse Coding for Adaptive Representation
27. ICML 2025Breaking Silos: Adaptive Model Fusion Unlocks Better Time Series Forecasting
28. ICML 2025Cache Me If You Must: Adaptive Key-Value Quantization for Large Language Models
29. ICML 2025Clipping Improves Adam-Norm and AdaGrad-Norm when the Noise Is Heavy-Tailed
30. ICML 2025COExpander: Adaptive Solution Expansion for Combinatorial Optimization
31. ICML 2025Cross-regularization: Adaptive Model Complexity through Validation Gradients
32. ICML 2025Dimension-Free Adaptive Subgradient Methods with Frequent Directions
33. ICML 2025Do Bayesian Neural Networks Actually Behave Like Bayesian Models?
34. ICML 2025Dual Feature Reduction for the Sparse-group Lasso and its Adaptive Variant
35. ICML 2025EvoMesh: Adaptive Physical Simulation with Hierarchical Graph Evolutions
36. ICML 2025Extracting Rare Dependence Patterns via Adaptive Sample Reweighting
37. ICML 2025Fast and Robust: Task Sampling with Posterior and Diversity Synergies for Adaptive Decision-Makers in Randomized Environments
38. ICML 2025Faster Stochastic Optimization with Arbitrary Delays via Adaptive Asynchronous Mini-Batching
39. ICML 2025FlexiReID: Adaptive Mixture of Expert for Multi-Modal Person Re-Identification
40. ICML 2025Focus On This, Not That! Steering LLMs with Adaptive Feature Specification
41. ICML 2025From Kernels to Features: A Multi-Scale Adaptive Theory of Feature Learning
42. ICML 2025GANQ: GPU-Adaptive Non-Uniform Quantization for Large Language Models
43. ICML 2025Gradient Descent Converges Arbitrarily Fast for Logistic Regression via Large and Adaptive Stepsizes
44. ICML 2025Graph Adaptive Autoregressive Moving Average Models
45. ICML 2025Layer-wise Quantization for Quantized Optimistic Dual Averaging
46. ICML 2025Learning Adaptive Lighting via Channel-Aware Guidance
47. ICML 2025Learning from Loss Landscape: Generalizable Mixed-Precision Quantization via Adaptive Sharpness-Aware Gradient Aligning
48. ICML 2025Learning to Trust Bellman Updates: Selective State-Adaptive Regularization for Offline RL
49. ICML 2025MAPLE: Many-Shot Adaptive Pseudo-Labeling for In-Context Learning
50. ICML 2025MARS: Unleashing the Power of Variance Reduction for Training Large Models

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。