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 47 篇，第 1 / 1 页

1. ICLR 2025AdaFisher: Adaptive Second Order Optimization via Fisher Information
2. ICLR 2025AdaGrad under Anisotropic Smoothness
3. ICLR 2025Adam Exploits $\ell_\infty$-geometry of Loss Landscape via Coordinate-wise Adaptivity
4. ICLR 2025ADAM Optimization with Adaptive Batch Selection
5. ICLR 2025Adaptive $Q$-Network: On-the-fly Target Selection for Deep Reinforcement Learning
6. ICLR 2025Adaptive backtracking line search
7. ICLR 2025Adaptive Batch Size for Privately Finding Second-Order Stationary Points
8. ICLR 2025Adaptive Length Image Tokenization via Recurrent Allocation
9. ICLR 2025Adaptive Methods through the Lens of SDEs: Theoretical Insights on the Role of Noise
10. ICLR 2025Adaptive Pruning of Pretrained Transformer via Differential Inclusions
11. ICLR 2025Adaptive Rank Allocation: Speeding Up Modern Transformers with RaNA Adapters
12. ICLR 2025Adaptive Shrinkage Estimation for Personalized Deep Kernel Regression in Modeling Brain Trajectories
13. ICLR 2025Adaptive teachers for amortized samplers
14. ICLR 2025Adaptive Transformer Programs: Bridging the Gap Between Performance and Interpretability in Transformers
15. ICLR 2025ASTrA: Adversarial Self-supervised Training with Adaptive-Attacks
16. ICLR 2025Breaking the $\log(1/\Delta_2)$ Barrier: Better Batched Best Arm Identification with Adaptive Grids
17. ICLR 2025Budgeted Online Continual Learning by Adaptive Layer Freezing and Frequency-based Sampling
18. ICLR 2025CAKE: Cascading and Adaptive KV Cache Eviction with Layer Preferences
19. ICLR 2025Complexity Lower Bounds of Adaptive Gradient Algorithms for Non-convex Stochastic Optimization under Relaxed Smoothness
20. ICLR 2025CONDA: Adaptive Concept Bottleneck for Foundation Models Under Distribution Shifts
21. ICLR 2025Convergence of Distributed Adaptive Optimization with Local Updates
22. ICLR 2025CoTFormer: A Chain of Thought Driven Architecture with Budget-Adaptive Computation Cost at Inference
23. ICLR 2025Data-adaptive Differentially Private Prompt Synthesis for In-Context Learning
24. ICLR 2025DenoiseVAE: Learning Molecule-Adaptive Noise Distributions for Denoising-based 3D Molecular Pre-training
25. ICLR 2025Dynamic Neural Fortresses: An Adaptive Shield for Model Extraction Defense
26. ICLR 2025Ensembling Diffusion Models via Adaptive Feature Aggregation
27. ICLR 2025Faster Cascades via Speculative Decoding
28. ICLR 2025FedLWS: Federated Learning with Adaptive Layer-wise Weight Shrinking
29. ICLR 2025From Attention to Activation: Unraveling the Enigmas of Large Language Models
30. ICLR 2025From Decoupling to Adaptive Transformation: a Wider Optimization Space for PTQ
31. ICLR 2025InstaTrain: Adaptive Training via Ultra-Fast Natural Annealing within Dynamical Systems
32. ICLR 2025Learning How Hard to Think: Input-Adaptive Allocation of LM Computation
33. ICLR 2025MatryoshkaKV: Adaptive KV Compression via Trainable Orthogonal Projection
34. ICLR 2025MIND over Body: Adaptive Thinking using Dynamic Computation
35. ICLR 2025Neural ODE Transformers: Analyzing Internal Dynamics and Adaptive Fine-tuning
36. ICLR 2025NExUME: Adaptive Training and Inference for DNNs under Intermittent Power Environments
37. ICLR 2025PEARL: Parallel Speculative Decoding with Adaptive Draft Length
38. ICLR 2025PIG: Physics-Informed Gaussians as Adaptive Parametric Mesh Representations
39. ICLR 2025Refine Knowledge of Large Language Models via Adaptive Contrastive Learning
40. ICLR 2025Revisit Micro-batch Clipping: Adaptive Data Pruning via Gradient Manipulation
41. ICLR 2025Scalable Universal T-Cell Receptor Embeddings from Adaptive Immune Repertoires
42. ICLR 2025SparsyFed: Sparse Adaptive Federated Learning
43. ICLR 2025Swift4D: Adaptive divide-and-conquer Gaussian Splatting for compact and efficient reconstruction of dynamic scene
44. ICLR 2025TAID: Temporally Adaptive Interpolated Distillation for Efficient Knowledge Transfer in Language Models
45. ICLR 2025Towards a General Time Series Anomaly Detector with Adaptive Bottlenecks and Dual Adversarial Decoders
46. ICLR 2025Towards Domain Adaptive Neural Contextual Bandits
47. ICLR 2025Towards Generalizable Reinforcement Learning via Causality-Guided Self-Adaptive Representations

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。