General ML · online learning papers, 2023–2026

Key findings

• General ML · online learning fell from 107 papers in 2023 to 105 in 2026, so interest is cooling.
• NeurIPS publishes the most General ML · online learning work: 199 papers from 2023 to 2026, 48% of the four-venue total.
• The fastest-growing overlap is with Theory · optimization: papers tagged with both rose from 0 in 2023 to 6 in 2026.
• Among the 6 topics under General Machine Learning, it ranks #6 by 2026 paper count; the fastest grower in the group, General ML · evaluation, is up 4.3x versus 1.0x here.

Representative papers

Spread across years and venues so every edition shows up

• 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

All General ML · online learning papers

105 papers, page 2 of 3

51. ICML 2026Online Continual Learning with Dynamic Label Hierarchies
52. ICML 2026Online Contract Design With Unknown Technology
53. ICML 2026Online Learning and Inference for Cox Proportional Hazards Model Using Renewable Sieve Estimation
54. ICML 2026Online Robust Reinforcement Learning with General Function Approximation
55. ICML 2026Online Rubrics Elicitation from Pairwise Comparisons
56. ICML 2026Optimal Learning from Label Proportions with General Loss Functions
57. ICML 2026Optimal Top-$k$ Identification from Pairwise Comparisons
58. ICML 2026Parsimonious Learning-Augmented Online Metric Matching
59. ICML 2026Relevance-Based Embeddings: Lightweight Candidate Retrieval via Heavy-Ranker Calls
60. ICML 2026Rethinking the Hardness of PbRL: A Provable General Regret Bound
61. ICML 2026Solving Time-Dependent Differential Equations with Physical Dynamical Systems
62. ICML 2026Stochastic Linear Bandits with Parameter Noise
63. ICML 2026Tempora: Characterising the Time-Contingent Utility of Online Test-Time Adaptation
64. ICML 2026The (Marginal) Value of a Search Ad: An Online Causal Framework for Repeated Second-price Auctions
65. ICML 2026The Cost of Information: Phase Transitions in Contextual Bandits with Paid Observations
66. ICML 2026The Cost of Learning Under Multiple Change Points
67. ICML 2026Ultrafast On-Chip Online Learning via Spline Locality in Kolmogorov–Arnold Networks
68. ICML 2026Understanding the Gaps in Satisficing Bandits
69. ICML 2026Universal Multiclass Transductive Online Learning
70. ICML 2026Upper-Linearizability of Online Non-Monotone DR-Submodular Maximization over Down-Closed Convex Sets
71. ICML 2026When Drafts Evolve: Speculative Decoding Meets Online Learning
72. NeurIPS 2026$\delta$-Mem: : Efficient Online Memory For Large Language Models
73. NeurIPS 2026A Compass for Useful Data: Online Data Selection via Alignment-Gated Fisher Geometry
74. NeurIPS 2026A Single-Sample Polylogarithmic Regret Bound for Nonstationary Online Linear Programming
75. NeurIPS 2026Agnostic Online Learning with Reliable Abstention
76. NeurIPS 2026Bian Que: An Agentic Framework with Flexible Skill Arrangement for Online System Operations
77. NeurIPS 2026Deployment-Time Online Imitation Learning from Corrective Demonstrations
78. NeurIPS 2026Evidence Guided Dual Expert Memory with Joint Routing for VLLMs Online Correction
79. NeurIPS 2026Flux: Online, Fine-Grained Data Scheduling for Training Machine Learning Interatomic Potentials
80. NeurIPS 2026From Generic to Dedicated: A Novel Optimizer for Online Continual Learning
81. NeurIPS 2026Improved Algorithms for Online Classification with Surrogate Losses
82. NeurIPS 2026Instance-Adaptive Online Multicalibration
83. NeurIPS 2026Learning-Augmented Online Scheduling with Parsimonious Preemption
84. NeurIPS 2026MIST: Reliable Streaming Decision Trees for Online Class-Incremental Learning via McDiarmid Bound
85. NeurIPS 2026Mixture-of-Experts for Online Matrix Completion on a Drifting Union of Subspaces
86. NeurIPS 2026Online Change-point Detection using Foundation Probabilistic Forecasting Models
87. NeurIPS 2026Online Control with Multiple Sensors
88. NeurIPS 2026Online Data Selection for Instruction Tuning via Gaussian Processes
89. NeurIPS 2026Online Fair Division Meets Reordering Buffers
90. NeurIPS 2026Online Learning via Learned Latent Bayesian Tracking
91. NeurIPS 2026Online Localized Conformal Prediction
92. NeurIPS 2026Online Maximization of Non-Decomposable Test and Population Utilities
93. NeurIPS 2026Online Minimum Description Length Passive-Aggressive Algorithms
94. NeurIPS 2026Online Quantile Omniprediction for Proper Losses
95. NeurIPS 2026Online Resource Allocation With General Constraints
96. NeurIPS 2026Optimal Hidden-Target Learning for Online Inventory Optimization on General Convex Sets
97. NeurIPS 2026Optimal Recalibration of an Online Predictor
98. NeurIPS 2026Optimistic Q-value Adaptation for Offline-to-Online Reinforcement Learning
99. NeurIPS 2026OWCE: Revealing Language Model Complementarity via Online Weakness-Conditioned Evaluation
100. NeurIPS 2026Regret–Oracle Complexity Tradeoffs in Agnostic Online Learning

FAQ

How many General ML · online learning papers were published at NeurIPS, ICLR, ICML and CVPR from 2023 to 2026?

416 in total: 107 in 2023, 96 in 2024, 108 in 2025, 105 in 2026.

How many General ML · online learning papers are at NeurIPS 2026?

NeurIPS 2026 has 34 General ML · online learning papers, versus 59 the year before.

How many General ML · online learning papers are at ICLR 2026?

ICLR 2026 has 13 General ML · online learning papers, versus 9 the year before.

How many General ML · online learning papers are at ICML 2026?

ICML 2026 has 49 General ML · online learning papers, versus 37 the year before.

How many General ML · online learning papers are at CVPR 2026?

CVPR 2026 has 9 General ML · online learning papers, versus 3 the year before.

Which conference publishes the most General ML · online learning papers?

NeurIPS, with 199 papers from 2023 to 2026.