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 80 篇，第 1 / 2 页

1. ICLR 2026A Convergence Analysis of Adaptive Optimizers under Floating-point Quantization
2. ICLR 2026A Tale of Two Smoothness Notions: Adaptive Optimizers and Non-Euclidean Descent
3. ICLR 2026Accelerating Diffusion Large Language Models with SlowFast Sampling: The Three Golden Principles
4. ICLR 2026AdaCache: Adaptive Caching and Context Augmentation for Efficient LLM Serving
5. ICLR 2026Adaptive Acquisition Selection for Bayesian Optimization with Large Language Models
6. ICLR 2026Adaptive Conformal Guidance for Learning under Uncertainty
7. ICLR 2026Adaptive Conformal Prediction via Mixture-of-Experts Gating Similarity
8. ICLR 2026Adaptive Gaussian Expansion for On-the-fly Category Discovery
9. ICLR 2026Adaptive Hopfield Network: Rethinking Similarities in Associative Memory
10. ICLR 2026Adaptive Logit Adjustment for Debiasing Multimodal Language Models
11. ICLR 2026Adaptive Mamba Neural Operators
12. ICLR 2026Adaptive Methods Are Preferable in High Privacy Settings: An SDE Perspective
13. ICLR 2026Adaptive Mixture of Disentangled Experts for Dynamic Graphs under Distribution Shifts
14. ICLR 2026Adaptive Moments are Surprisingly Effective for Plug-and-Play Diffusion Sampling
15. ICLR 2026Adaptive Nonlinear Compression for Large Foundation Models
16. ICLR 2026Adaptive Regularization for Large-Scale Sparse Feature Embedding Models
17. ICLR 2026Adaptive Rollout Allocation for Online Reinforcement Learning with Verifiable Rewards
18. ICLR 2026Adaptive Scaling of Policy Constraints for Offline Reinforcement Learning
19. ICLR 2026Adaptive Thinking: Large Language Models Know When to Think in Latent Space
20. ICLR 2026Adaptive Width Neural Networks
21. ICLR 2026AdaRank: Adaptive Rank Pruning for Enhanced Model Merging
22. ICLR 2026AdaSpec: Adaptive Spectrum for Enhanced Node Distinguishability
23. ICLR 2026ADEPT: Continual Pretraining via Adaptive Expansion and Dynamic Decoupled Tuning
24. ICLR 2026AFTER: Mitigating the Object Hallucination of LVLM via Adaptive Factual-Guided Activation Editing
25. ICLR 2026APC-RL: Exceeding data-driven behavior priors with adaptive policy composition
26. ICLR 2026ARMOR: High-Performance Semi-Structured Pruning via Adaptive Matrix Factorization
27. ICLR 2026ASTGI: Adaptive Spatio-Temporal Graph Interactions for Irregular Multivariate Time Series Forecasting
28. ICLR 2026Automated Stateful Specialization for Adaptive Agent Systems
29. ICLR 2026ByteFlow: Language Modeling through Adaptive Byte Compression without a Tokenizer
30. ICLR 2026Code Driven Planning with Domain-Adaptive Selector
31. ICLR 2026CooperTrim: Adaptive Data Selection for Uncertainty-Aware Cooperative Perception
32. ICLR 2026COSMOS: A Hybrid Adaptive Optimizer for Efficient Training of Large Language Models
33. ICLR 2026d$^2$Cache: Accelerating Diffusion-Based LLMs via Dual Adaptive Caching
34. ICLR 2026Deep Hierarchical Learning with Nested Subspace Networks
35. ICLR 2026DES-LOC: Desynced Low Communication Adaptive Optimizers for Foundation Models
36. ICLR 2026Dynamic-dLLM: Dynamic Cache-Budget and Adaptive Parallel Decoding for Training-Free Acceleration of Diffusion LLM
37. ICLR 2026E²LoRA: Efficient and Effective Low-Rank Adaptation with Entropy-Guided Adaptive Sharing
38. ICLR 2026Expressive yet Efficient Feature Expansion with Adaptive Cross-Hadamard Products
39. ICLR 2026Fairness-Aware Multi-view Evidential Learning with Adaptive Prior
40. ICLR 2026Fast Frank–Wolfe Algorithms with Adaptive Bregman Step-Size for Weakly Convex Functions
41. ICLR 2026FutureMind: Equipping Small Language Models with Strategic Thinking-Pattern Priors via Adaptive Knowledge Distillation
42. ICLR 2026FZOO: Fast Zeroth-Order Optimizer for Fine‑Tuning Large Language Models towards Adam‑Scale Speed
43. ICLR 2026Graph Signal Processing Meets Mamba2: Adaptive Filter Bank via Delta Modulation
44. ICLR 2026High-dimensional limit theorems for SGD: Momentum and Adaptive Step-sizes
45. ICLR 2026Implicit Bias of Per-sample Adam on Separable Data: Departure from the Full-batch Regime
46. ICLR 2026Instance-wise Adaptive Scheduling via Derivative-Free Meta-Learning
47. ICLR 2026JAPAN: Joint Adaptive Prediction Areas with Normalising Flow
48. ICLR 2026Learn to Reason Efficiently with Adaptive Length-based Reward Shaping
49. ICLR 2026Learning To Draft: Adaptive Speculative Decoding with Reinforcement Learning
50. ICLR 2026Learning to Parallel: Accelerating Diffusion Large Language Models via Adaptive Parallel Decoding

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。