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 61 篇，第 1 / 2 页

1. ICML 2025A Generalization Result for Convergence in Learning-to-Optimize
2. ICML 2025A Manifold Perspective on the Statistical Generalization of Graph Neural Networks
3. ICML 2025A Meta-learner for Heterogeneous Effects in Difference-in-Differences
4. ICML 2025A Theoretical Study of (Hyper) Self-Attention through the Lens of Interactions: Representation, Training, Generalization
5. ICML 2025A Unified Framework for Generalization Error Analysis of Learning with Arbitrary Discrete Weak Features
6. ICML 2025Adversarial Robust Generalization of Graph Neural Networks
7. ICML 2025Avoiding spurious sharpness minimization broadens applicability of SAM
8. ICML 2025Causality Inspired Federated Learning for OOD Generalization
9. ICML 2025Compositional Generalization via Forced Rendering of Disentangled Latents
10. ICML 2025Compositional Risk Minimization
11. ICML 2025Controlling Neural Collapse Enhances Out-of-Distribution Detection and Transfer Learning
12. ICML 2025Covered Forest: Fine-grained generalization analysis of graph neural networks
13. ICML 2025Discrepancies are Virtue: Weak-to-Strong Generalization through Lens of Intrinsic Dimension
14. ICML 2025Does Data Scaling Lead to Visual Compositional Generalization?
15. ICML 2025Enhancing Graph Invariant Learning from a Negative Inference Perspective
16. ICML 2025Exactly Tight Information-theoretic Generalization Bounds via Binary Jensen-Shannon Divergence
17. ICML 2025Federated Learning for Feature Generalization with Convex Constraints
18. ICML 2025FedSMU: Communication-Efficient and Generalization-Enhanced Federated Learning through Symbolic Model Updates
19. ICML 2025Fourier Position Embedding: Enhancing Attention’s Periodic Extension for Length Generalization
20. ICML 2025Generalization Analysis for Controllable Learning
21. ICML 2025Generalization Bounds via Meta-Learned Model Representations: PAC-Bayes and Sample Compression Hypernetworks
22. ICML 2025Generalization in Federated Learning: A Conditional Mutual Information Framework
23. ICML 2025Generalization of noisy SGD in unbounded non-convex settings
24. ICML 2025Generalization Performance of Ensemble Clustering: From Theory to Algorithm
25. ICML 2025Generalizing Causal Effects from Randomized Controlled Trials to Target Populations across Diverse Environments
26. ICML 2025Generative Intervention Models for Causal Perturbation Modeling
27. ICML 2025Grokking Beyond the Euclidean Norm of Model Parameters
28. ICML 2025Hide & Seek: Transformer Symmetries Obscure Sharpness & Riemannian Geometry Finds It
29. ICML 2025Improving Generalization in Federated Learning with Highly Heterogeneous Data via Momentum-Based Stochastic Controlled Weight Averaging
30. ICML 2025Improving Generalization with Flat Hilbert Bayesian Inference
31. ICML 2025In-Context Learning and Occam's Razor
32. ICML 2025Investigating the Overlooked Hessian Structure: From CNNs to LLMs
33. ICML 2025IT$^3$: Idempotent Test-Time Training
34. ICML 2025Learning Input Encodings for Kernel-Optimal Implicit Neural Representations
35. ICML 2025Learning Time-Aware Causal Representation for Model Generalization in Evolving Domains
36. ICML 2025LightGTS: A Lightweight General Time Series Forecasting Model
37. ICML 2025Multivariate Conformal Selection
38. ICML 2025No-Regret is not enough! Bandits with General Constraints through Adaptive Regret Minimization
39. ICML 2025Non-Asymptotic Length Generalization
40. ICML 2025On the Generalization Ability of Next-Token-Prediction Pretraining
41. ICML 2025On the Out-of-Distribution Generalization of Self-Supervised Learning
42. ICML 2025On the Statistical Mechanisms of Distributional Compositional Generalization
43. ICML 2025One-Step Generalization Ratio Guided Optimization for Domain Generalization
44. ICML 2025OOD-Chameleon: Is Algorithm Selection for OOD Generalization Learnable?
45. ICML 2025Position: Deep Learning is Not So Mysterious or Different
46. ICML 2025Position: General Intelligence Requires Reward-based Pretraining
47. ICML 2025Provable Length Generalization in Sequence Prediction via Spectral Filtering
48. ICML 2025Provably Improving Generalization of Few-shot models with Synthetic Data
49. ICML 2025QT-DoG: Quantization-Aware Training for Domain Generalization
50. ICML 2025Relating Misfit to Gain in Weak-to-Strong Generalization Beyond the Squared Loss

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。