域适应论文趋势 2023–2026

主要结论

• 域适应论文从 2023 年的 174 篇增长到 2026 年的 263 篇，三年间扩大到约 1.5 倍。
• CVPR 是发域适应论文最多的会议，2023–2026 年共 268 篇，占四个会议总量的 31%。
• 交叉方向里涨得最快的是多模态大模型：同时属于两个主题的论文从 2023 年的 7 篇增至 2026 年的 38 篇。
• 在「元学习与迁移」的 5 个主题里，它的 2026 年论文数排第 3；同组增长最快的基础模型适配是 3.8 倍，域适应是 1.5 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 2026A Dual-Domain Vision Transformer with Spectral Positional Bias
• ICML 2026Bayesian Meta-Learning with Expert Feedback for Task-Shift Adaptation through Causal Embeddings
• ICLR 2026Bayesian Evidence-Driven Prototype Evolution for Federated Domain Adaptation
• CVPR 2026Anatomical Domain Shifts Test-time Heterogeneous Adaptation for 3D Human Pose
• NeurIPS 20253DPE-Gaze:Unlocking the Potential of 3D Facial Priors for Generalized Gaze Estimation
• ICML 2025A General Representation-Based Approach to Multi-Source Domain Adaptation
• ICLR 2025Adaptive Energy Alignment for Accelerating Test-Time Adaptation
• CVPR 2025A4A: Adapter for Adapter Transfer via All-for-All Mapping for Cross-Architecture Models
• NeurIPS 2024A Cross-Domain Benchmark for Active Learning
• ICML 2024Batch Singular Value Polarization and Weighted Semantic Augmentation for Universal Domain Adaptation
• ICLR 2024Adapting Large Language Models via Reading Comprehension
• CVPR 2024Day-Night Cross-domain Vehicle Re-identification
• NeurIPS 2023(Almost) Provable Error Bounds Under Distribution Shift via Disagreement Discrepancy
• ICML 2023In Search for a Generalizable Method for Source Free Domain Adaptation
• ICLR 2023Addressing Parameter Choice Issues in Unsupervised Domain Adaptation by Aggregation
• CVPR 2023A New Benchmark: On the Utility of Synthetic Data With Blender for Bare Supervised Learning and Downstream Domain Adaptation
• NeurIPS 2026A unified pairwise distribution matching framework for graph domain adaptation under structure shift
• ICML 2026Content-Style Identification via Differential Independence
• ICLR 2026Beyond In-Domain Detection: SpikeScore for Cross-Domain Hallucination Detection
• CVPR 2026Bridge Basis-Driven Causal Inference Marries VFMs for Domain Generalization

全部域适应论文

共 37 篇，第 1 / 1 页

1. ICML 2024Adversarially Robust Hypothesis Transfer Learning
2. ICML 2024Batch Singular Value Polarization and Weighted Semantic Augmentation for Universal Domain Adaptation
3. ICML 2024Bayesian Power Steering: An Effective Approach for Domain Adaptation of Diffusion Models
4. ICML 2024BECoTTA: Input-dependent Online Blending of Experts for Continual Test-time Adaptation
5. ICML 2024Category-Aware Active Domain Adaptation
6. ICML 2024CauDiTS: Causal Disentangled Domain Adaptation of Multivariate Time Series
7. ICML 2024Compressible Dynamics in Deep Overparameterized Low-Rank Learning & Adaptation
8. ICML 2024Contrastive Representation for Data Filtering in Cross-Domain Offline Reinforcement Learning
9. ICML 2024Covert Malicious Finetuning: Challenges in Safeguarding LLM Adaptation
10. ICML 2024Cross-domain Open-world Discovery
11. ICML 2024Cross-Domain Policy Adaptation by Capturing Representation Mismatch
12. ICML 2024Differentially Private Domain Adaptation with Theoretical Guarantees
13. ICML 2024DOGE: Domain Reweighting with Generalization Estimation
14. ICML 2024Domain Generalisation via Imprecise Learning
15. ICML 2024Domain-wise Data Acquisition to Improve Performance under Distribution Shift
16. ICML 2024DoRA: Weight-Decomposed Low-Rank Adaptation
17. ICML 2024DSD-DA: Distillation-based Source Debiasing for Domain Adaptive Object Detection
18. ICML 2024Getting the most out of your tokenizer for pre-training and domain adaptation
19. ICML 2024Gradual Divergence for Seamless Adaptation: A Novel Domain Incremental Learning Method
20. ICML 2024Hyperbolic Active Learning for Semantic Segmentation under Domain Shift
21. ICML 2024Incorporating probabilistic domain knowledge into deep multiple instance learning
22. ICML 2024IW-GAE: Importance weighted group accuracy estimation for improved calibration and model selection in unsupervised domain adaptation
23. ICML 2024Large Scale Dataset Distillation with Domain Shift
24. ICML 2024Learning Causal Domain-Invariant Temporal Dynamics for Few-Shot Action Recognition
25. ICML 2024LoRA+: Efficient Low Rank Adaptation of Large Models
26. ICML 2024MOKD: Cross-domain Finetuning for Few-shot Classification via Maximizing Optimized Kernel Dependence
27. ICML 2024Pairwise Alignment Improves Graph Domain Adaptation
28. ICML 2024Pseudo-Calibration: Improving Predictive Uncertainty Estimation in Unsupervised Domain Adaptation
29. ICML 2024Reducing Item Discrepancy via Differentially Private Robust Embedding Alignment for Privacy-Preserving Cross Domain Recommendation
30. ICML 2024Rethinking DP-SGD in Discrete Domain: Exploring Logistic Distribution in the Realm of signSGD
31. ICML 2024RoSA: Accurate Parameter-Efficient Fine-Tuning via Robust Adaptation
32. ICML 2024Stationary Latent Weight Inference for Unreliable Observations from Online Test-Time Adaptation
33. ICML 2024SuDA: Support-based Domain Adaptation for Sim2Real Hinge Joint Tracking with Flexible Sensors
34. ICML 2024TabLog: Test-Time Adaptation for Tabular Data Using Logic Rules
35. ICML 2024Test-Time Model Adaptation with Only Forward Passes
36. ICML 2024Time Series Diffusion in the Frequency Domain
37. ICML 2024Unsupervised Domain Adaptation for Anatomical Structure Detection in Ultrasound Images

常见问题

2023–2026 年四大会议一共有多少篇域适应论文？

共 866 篇，按年份分别是 2023 年 174 篇、2024 年 209 篇、2025 年 220 篇、2026 年 263 篇。

NeurIPS 2026 有多少篇域适应论文？

NeurIPS 2026 有 78 篇域适应论文，上一届是 81 篇。

ICLR 2026 有多少篇域适应论文？

ICLR 2026 有 46 篇域适应论文，上一届是 45 篇。

ICML 2026 有多少篇域适应论文？

ICML 2026 有 69 篇域适应论文，上一届是 48 篇。

CVPR 2026 有多少篇域适应论文？

CVPR 2026 有 70 篇域适应论文，上一届是 46 篇。

哪个会议的域适应论文最多？

CVPR，2023–2026 年共 268 篇。