通用机器学习 · generalization论文趋势 2023–2026

主要结论

• 通用机器学习 · generalization论文从 2023 年的 136 篇增长到 2026 年的 152 篇，三年间扩大到约 1.1 倍。
• NeurIPS 是发通用机器学习 · generalization论文最多的会议，2023–2026 年共 207 篇，占四个会议总量的 35%。
• 交叉方向里涨得最快的是理论 · learning theory：同时属于两个主题的论文从 2023 年的 3 篇增至 2026 年的 20 篇。
• 在「通用机器学习」的 6 个主题里，它的 2026 年论文数排第 5；同组增长最快的通用机器学习 · evaluation是 4.3 倍，通用机器学习 · generalization是 1.1 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 2026Asymmetric Generalization in Deep CTR Models: A Block-wise Diagnosis
• ICML 2026Anti-causal domain generalization: Leveraging unlabeled data
• ICLR 2026Generalization Below the Edge of Stability: The Role of Data Geometry
• CVPR 2026PriVi Towards a General-Purpose Video Model for Primate Behavior in
• NeurIPS 2025Automatic Visual Instrumental Variable Learning for Confounding-Resistant Domain Generalization
• ICML 2025Causality Inspired Federated Learning for OOD Generalization
• ICLR 2025Federated Domain Generalization with Data-free On-server Matching Gradient
• CVPR 2025Balanced Direction from Multifarious Choices: Arithmetic Meta-Learning for Domain Generalization
• NeurIPS 2024Benchmarking Out-of-Distribution Generalization Capabilities of DNN-based Encoding Models for the Ventral Visual Cortex.
• ICML 2024Algorithmic Stability Unleashed: Generalization Bounds with Unbounded Losses
• ICLR 2024Adaptive Sharpness-Aware Pruning for Robust Sparse Networks
• CVPR 2024Disentangled Prompt Representation for Domain Generalization
• NeurIPS 2023A unified framework for information-theoretic generalization bounds
• ICML 2023Algorithmic Stability of Heavy-Tailed SGD with General Loss Functions
• ICLR 2023ArCL: Enhancing Contrastive Learning with Augmentation-Robust Representations
• CVPR 2023AltFreezing for More General Video Face Forgery Detection
• NeurIPS 2026Beyond Average Flatness: Domain-wise Flatness for Domain Generalization
• ICML 2026Are Object-Centric Representations Better at Compositional Generalization?
• ICLR 2026Temporal Generalization: A Reality Check
• CVPR 2026The Golden Subspace Where Efficiency Meets Generalization in Continual Test-Time

全部通用机器学习 · generalization论文

共 136 篇，第 1 / 3 页

1. CVPR 2023ALOFT: A Lightweight MLP-Like Architecture With Dynamic Low-Frequency Transform for Domain Generalization
2. CVPR 2023AltFreezing for More General Video Face Forgery Detection
3. CVPR 2023Bi-Level Meta-Learning for Few-Shot Domain Generalization
4. CVPR 2023Crossing the Gap: Domain Generalization for Image Captioning
5. CVPR 2023DART: Diversify-Aggregate-Repeat Training Improves Generalization of Neural Networks
6. CVPR 2023Decompose, Adjust, Compose: Effective Normalization by Playing With Frequency for Domain Generalization
7. CVPR 2023Deep Frequency Filtering for Domain Generalization
8. CVPR 2023Federated Domain Generalization With Generalization Adjustment
9. CVPR 2023HumanBench: Towards General Human-Centric Perception With Projector Assisted Pretraining
10. CVPR 2023Implicit Identity Leakage: The Stumbling Block to Improving Deepfake Detection Generalization
11. CVPR 2023Improving Generalization of Meta-Learning With Inverted Regularization at Inner-Level
12. CVPR 2023Improving Generalization With Domain Convex Game
13. CVPR 2023Improving Robust Generalization by Direct PAC-Bayesian Bound Minimization
14. CVPR 2023Instance-Aware Domain Generalization for Face Anti-Spoofing
15. CVPR 2023Meta Omnium: A Benchmark for General-Purpose Learning-To-Learn
16. CVPR 2023Mind the Label Shift of Augmentation-Based Graph OOD Generalization
17. CVPR 2023MMG-Ego4D: Multimodal Generalization in Egocentric Action Recognition
18. CVPR 2023Modality-Agnostic Debiasing for Single Domain Generalization
19. CVPR 2023Neuralizer: General Neuroimage Analysis Without Re-Training
20. CVPR 2023NICO++: Towards Better Benchmarking for Domain Generalization
21. CVPR 2023Progressive Random Convolutions for Single Domain Generalization
22. CVPR 2023Promoting Semantic Connectivity: Dual Nearest Neighbors Contrastive Learning for Unsupervised Domain Generalization
23. CVPR 2023Robust Generalization Against Photon-Limited Corruptions via Worst-Case Sharpness Minimization
24. CVPR 2023Sharpness-Aware Gradient Matching for Domain Generalization
25. CVPR 2023Simulated Annealing in Early Layers Leads to Better Generalization
26. ICLR 2023A new characterization of the edge of stability based on a sharpness measure aware of batch gradient distribution
27. ICLR 2023Agree to Disagree: Diversity through Disagreement for Better Transferability
28. ICLR 2023ArCL: Enhancing Contrastive Learning with Augmentation-Robust Representations
29. ICLR 2023Benign Overfitting in Classification: Provably Counter Label Noise with Larger Models
30. ICLR 2023Can Agents Run Relay Race with Strangers? Generalization of RL to Out-of-Distribution Trajectories
31. ICLR 2023Causal Balancing for Domain Generalization
32. ICLR 2023Compositional Semantic Parsing with Large Language Models
33. ICLR 2023Compositionality with Variation Reliably Emerges in Neural Networks
34. ICLR 2023Cycle-consistent Masked AutoEncoder for Unsupervised Domain Generalization
35. ICLR 2023Data Valuation Without Training of a Model
36. ICLR 2023Dataset Pruning: Reducing Training Data by Examining Generalization Influence
37. ICLR 2023Disentanglement of Correlated Factors via Hausdorff Factorized Support
38. ICLR 2023Disentangling the Mechanisms Behind Implicit Regularization in SGD
39. ICLR 2023Domain Generalization via Heckman-type Selection Models
40. ICLR 2023Exponential Generalization Bounds with Near-Optimal Rates for $L_q$-Stable Algorithms
41. ICLR 2023FedSpeed: Larger Local Interval, Less Communication Round, and Higher Generalization Accuracy
42. ICLR 2023GAIN: On the Generalization of Instructional Action Understanding
43. ICLR 2023Hierarchical Abstraction for Combinatorial Generalization in Object Rearrangement
44. ICLR 2023Improving Out-of-distribution Generalization with Indirection Representations
45. ICLR 2023Joint Edge-Model Sparse Learning is Provably Efficient for Graph Neural Networks
46. ICLR 2023Leveraging Unlabeled Data to Track Memorization
47. ICLR 2023Linear Connectivity Reveals Generalization Strategies
48. ICLR 2023Loss Landscapes are All You Need: Neural Network Generalization Can Be Explained Without the Implicit Bias of Gradient Descent
49. ICLR 2023Max-Margin Works while Large Margin Fails: Generalization without Uniform Convergence
50. ICLR 2023Neural Networks Efficiently Learn Low-Dimensional Representations with SGD

常见问题

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

共 592 篇，按年份分别是 2023 年 136 篇、2024 年 135 篇、2025 年 169 篇、2026 年 152 篇。

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

NeurIPS 2026 有 58 篇通用机器学习 · generalization论文，上一届是 61 篇。

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

ICLR 2026 有 38 篇通用机器学习 · generalization论文，上一届是 33 篇。

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

ICML 2026 有 47 篇通用机器学习 · generalization论文，上一届是 61 篇。

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

CVPR 2026 有 9 篇通用机器学习 · generalization论文，上一届是 14 篇。

哪个会议的通用机器学习 · generalization论文最多？

NeurIPS，2023–2026 年共 207 篇。