通用机器学习 · online learning论文趋势 2023–2026

主要结论

• 通用机器学习 · online learning论文从 2023 年的 107 篇降到 2026 年的 105 篇，热度在回落。
• NeurIPS 是发通用机器学习 · online learning论文最多的会议，2023–2026 年共 199 篇，占四个会议总量的 48%。
• 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 0 篇增至 2026 年的 6 篇。
• 在「通用机器学习」的 6 个主题里，它的 2026 年论文数排第 6；同组增长最快的通用机器学习 · evaluation是 4.3 倍，通用机器学习 · online learning是 1.0 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 2026$\delta$-Mem: : Efficient Online Memory For Large Language Models
• ICML 2026Beyond Point-wise Neural Collapse: A Topology-Aware Hierarchical Classifier for Class-Incremental Learning
• ICLR 2026Rethinking Data Curation in LLM Training: Online Reweighting Offers Better Generalization than Offline Methods
• CVPR 2026Dynamic Momentum Recalibration in Online Gradient Learning
• NeurIPS 2025$O(\sqrt{T})$ Static Regret and Instance Dependent Constraint Violation for Constrained Online Convex Optimization
• ICML 2025A Online Statistical Framework for Out-of-Distribution Detection
• ICLR 2025Event-Driven Online Vertical Federated Learning
• CVPR 2025InteractionMap: Improving Online Vectorized HDMap Construction with Interaction
• NeurIPS 2024A Theory of Optimistically Universal Online Learnability for General Concept Classes
• ICML 2024A General Online Algorithm for Optimizing Complex Performance Metrics
• ICLR 2024Learning No-Regret Sparse Generalized Linear Models with Varying Observation(s)
• CVPR 2024Dual-Enhanced Coreset Selection with Class-wise Collaboration for Online Blurry Class Incremental Learning
• NeurIPS 2023A Batch-to-Online Transformation under Random-Order Model
• ICML 2023Banker Online Mirror Descent: A Universal Approach for Delayed Online Bandit Learning
• ICLR 2023Online Bias Correction for Task-Free Continual Learning
• CVPR 2023VisFusion: Visibility-Aware Online 3D Scene Reconstruction From Videos
• NeurIPS 2026A Single-Sample Polylogarithmic Regret Bound for Nonstationary Online Linear Programming
• ICML 2026CARE: Adaptive Calibration for Reliable Recommendations
• ICLR 2026Semi-Parametric Contextual Pricing with General Smoothness
• CVPR 2026Online3R Online Learning for Consistent Sequential Reconstruction Based on Geometry

全部通用机器学习 · online learning论文

共 199 篇，第 1 / 4 页

1. NeurIPS 2026$\delta$-Mem: : Efficient Online Memory For Large Language Models
2. NeurIPS 2026A Compass for Useful Data: Online Data Selection via Alignment-Gated Fisher Geometry
3. NeurIPS 2026A Single-Sample Polylogarithmic Regret Bound for Nonstationary Online Linear Programming
4. NeurIPS 2026Agnostic Online Learning with Reliable Abstention
5. NeurIPS 2026Bian Que: An Agentic Framework with Flexible Skill Arrangement for Online System Operations
6. NeurIPS 2026Deployment-Time Online Imitation Learning from Corrective Demonstrations
7. NeurIPS 2026Evidence Guided Dual Expert Memory with Joint Routing for VLLMs Online Correction
8. NeurIPS 2026Flux: Online, Fine-Grained Data Scheduling for Training Machine Learning Interatomic Potentials
9. NeurIPS 2026From Generic to Dedicated: A Novel Optimizer for Online Continual Learning
10. NeurIPS 2026Improved Algorithms for Online Classification with Surrogate Losses
11. NeurIPS 2026Instance-Adaptive Online Multicalibration
12. NeurIPS 2026Learning-Augmented Online Scheduling with Parsimonious Preemption
13. NeurIPS 2026MIST: Reliable Streaming Decision Trees for Online Class-Incremental Learning via McDiarmid Bound
14. NeurIPS 2026Mixture-of-Experts for Online Matrix Completion on a Drifting Union of Subspaces
15. NeurIPS 2026Online Change-point Detection using Foundation Probabilistic Forecasting Models
16. NeurIPS 2026Online Control with Multiple Sensors
17. NeurIPS 2026Online Data Selection for Instruction Tuning via Gaussian Processes
18. NeurIPS 2026Online Fair Division Meets Reordering Buffers
19. NeurIPS 2026Online Learning via Learned Latent Bayesian Tracking
20. NeurIPS 2026Online Localized Conformal Prediction
21. NeurIPS 2026Online Maximization of Non-Decomposable Test and Population Utilities
22. NeurIPS 2026Online Minimum Description Length Passive-Aggressive Algorithms
23. NeurIPS 2026Online Quantile Omniprediction for Proper Losses
24. NeurIPS 2026Online Resource Allocation With General Constraints
25. NeurIPS 2026Optimal Hidden-Target Learning for Online Inventory Optimization on General Convex Sets
26. NeurIPS 2026Optimal Recalibration of an Online Predictor
27. NeurIPS 2026Optimistic Q-value Adaptation for Offline-to-Online Reinforcement Learning
28. NeurIPS 2026OWCE: Revealing Language Model Complementarity via Online Weakness-Conditioned Evaluation
29. NeurIPS 2026Regret–Oracle Complexity Tradeoffs in Agnostic Online Learning
30. NeurIPS 2026Tackling the Data-Parallel Load Balancing Bottleneck in LLM Serving: Practical Online Routing at Scale
31. NeurIPS 2026The Minimax Rate of Online Isotonic Regression on Product Orders
32. NeurIPS 2026The Power of a Random Sample in Online Algorithms
33. NeurIPS 2026Token Filtering: Online Attention Pruning via KV Similarity for Efficient LLM Inference
34. NeurIPS 2026When Does Online Imitation Learning Help in LLM Post-Training? The Role of (Non-)Realizability Beyond Horizon
35. NeurIPS 2025$O(\sqrt{T})$ Static Regret and Instance Dependent Constraint Violation for Constrained Online Convex Optimization
36. NeurIPS 2025A Learning-Augmented Approach to Online Allocation Problems
37. NeurIPS 2025Agnostic Continuous-Time Online Learning
38. NeurIPS 2025Asymptotic theory of SGD with a general learning-rate
39. NeurIPS 2025Beyond $\tilde{O}(\sqrt{T})$ Constraint Violation for Online Convex Optimization with Adversarial Constraints
40. NeurIPS 2025Computable universal online learning
41. NeurIPS 2025Conformal Online Learning of Deep Koopman Linear Embeddings
42. NeurIPS 2025Contextual Online Pricing with (Biased) Offline Data
43. NeurIPS 2025DAA: Amplifying Unknown Discrepancy for Test-Time Discovery
44. NeurIPS 2025Distribution Learning Meets Graph Structure Sampling
45. NeurIPS 2025Dynamic Regret Reduces to Kernelized Static Regret
46. NeurIPS 2025Exploring the Noise Robustness of Online Conformal Prediction
47. NeurIPS 2025Generalized Linear Bandits: Almost Optimal Regret with One-Pass Update
48. NeurIPS 2025Gradient-Variation Online Adaptivity for Accelerated Optimization with Hölder Smoothness
49. NeurIPS 2025Improved Confidence Regions and Optimal Algorithms for Online and Offline Linear MNL Bandits
50. NeurIPS 2025Improving LLM General Preference Alignment via Optimistic Online Mirror Descent

常见问题

2023–2026 年四大会议一共有多少篇通用机器学习 · online learning论文？

共 416 篇，按年份分别是 2023 年 107 篇、2024 年 96 篇、2025 年 108 篇、2026 年 105 篇。

NeurIPS 2026 有多少篇通用机器学习 · online learning论文？

NeurIPS 2026 有 34 篇通用机器学习 · online learning论文，上一届是 59 篇。

ICLR 2026 有多少篇通用机器学习 · online learning论文？

ICLR 2026 有 13 篇通用机器学习 · online learning论文，上一届是 9 篇。

ICML 2026 有多少篇通用机器学习 · online learning论文？

ICML 2026 有 49 篇通用机器学习 · online learning论文，上一届是 37 篇。

CVPR 2026 有多少篇通用机器学习 · online learning论文？

CVPR 2026 有 9 篇通用机器学习 · online learning论文，上一届是 3 篇。

哪个会议的通用机器学习 · online learning论文最多？

NeurIPS，2023–2026 年共 199 篇。