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 220 篇，第 3 / 5 页

101. ICML 2025COSDA: Counterfactual-based Susceptibility Risk Framework for Open-Set Domain Adaptation
102. ICML 2025Disentangled Graph Spectral Domain Adaptation
103. ICML 2025DPCore: Dynamic Prompt Coreset for Continual Test-Time Adaptation
104. ICML 2025ExPLoRA: Parameter-Efficient Extended Pre-Training to Adapt Vision Transformers under Domain Shifts
105. ICML 2025FedPHA: Federated Prompt Learning for Heterogeneous Client Adaptation
106. ICML 2025Flowing Datasets with Wasserstein over Wasserstein Gradient Flows
107. ICML 2025Function Encoders: A Principled Approach to Transfer Learning in Hilbert Spaces
108. ICML 2025GCAL: Adapting Graph Models to Evolving Domain Shifts
109. ICML 2025Generalizable Multi-Camera 3D Object Detection from a Single Source via Fourier Cross-View Learning
110. ICML 2025GS-Bias: Global-Spatial Bias Learner for Single-Image Test-Time Adaptation of Vision-Language Models
111. ICML 2025Heterogeneous Label Shift: Theory and Algorithm
112. ICML 2025Homophily Enhanced Graph Domain Adaptation
113. ICML 2025How Much Can Transfer? BRIDGE: Bounded Multi-Domain Graph Foundation Model with Generalization Guarantees
114. ICML 2025MaskTwins: Dual-form Complementary Masking for Domain-Adaptive Image Segmentation
115. ICML 2025Merge-Friendly Post-Training Quantization for Multi-Target Domain Adaptation
116. ICML 2025Multi-Domain Graph Foundation Models: Robust Knowledge Transfer via Topology Alignment
117. ICML 2025Mutual Learning for SAM Adaptation: A Dual Collaborative Network Framework for Source-Free Domain Transfer
118. ICML 2025Neutral residues: revisiting adapters for model extension
119. ICML 2025Optimal Transfer Learning for Missing Not-at-Random Matrix Completion
120. ICML 2025QT-DoG: Quantization-Aware Training for Domain Generalization
121. ICML 2025Random Registers for Cross-Domain Few-Shot Learning
122. ICML 2025Revisiting Continuity of Image Tokens for Cross-domain Few-shot Learning
123. ICML 2025Self-Bootstrapping for Versatile Test-Time Adaptation
124. ICML 2025Self-Disentanglement and Re-Composition for Cross-Domain Few-Shot Segmentation
125. ICML 2025Set Valued Predictions For Robust Domain Generalization
126. ICML 2025Soup-of-Experts: Pretraining Specialist Models via Parameters Averaging
127. ICML 2025Sparse Causal Discovery with Generative Intervention for Unsupervised Graph Domain Adaptation
128. ICML 2025SynEVO: A neuro-inspired spatiotemporal evolutional framework for cross-domain adaptation
129. ICML 2025Tackling Dimensional Collapse toward Comprehensive Universal Domain Adaptation
130. ICML 2025Test-Time Adaptation with Binary Feedback
131. ICML 2025The Role of Sparsity for Length Generalization in LLMs
132. ICML 2025Theoretical Performance Guarantees for Partial Domain Adaptation via Partial Optimal Transport
133. ICML 2025Transfer Learning for Nonparametric Contextual Dynamic Pricing
134. ICML 2025TransPL: VQ-Code Transition Matrices for Pseudo-Labeling of Time Series Unsupervised Domain Adaptation
135. ICML 2025Unveiling Markov heads in Pretrained Language Models for Offline Reinforcement Learning
136. ICML 2025When can in-context learning generalize out of task distribution?
137. ICML 2025When Can Proxies Improve the Sample Complexity of Preference Learning?
138. ICML 2025World Model Implanting for Test-time Adaptation of Embodied Agents
139. ICML 2025Zebra: In-Context Generative Pretraining for Solving Parametric PDEs
140. NeurIPS 20253DPE-Gaze:Unlocking the Potential of 3D Facial Priors for Generalized Gaze Estimation
141. NeurIPS 2025A Generalized Label Shift Perspective for Cross-Domain Gaze Estimation
142. NeurIPS 2025AltLoRA: Towards Better Gradient Approximation in Low-Rank Adaptation with Alternating Projections
143. NeurIPS 2025Automatic Visual Instrumental Variable Learning for Confounding-Resistant Domain Generalization
144. NeurIPS 2025Beyond Higher Rank: Token-wise Input-Output Projections for Efficient Low-Rank Adaptation
145. NeurIPS 2025Breakthrough Sensor-Limited Single View: Towards Implicit Temporal Dynamics for Time Series Domain Adaptation
146. NeurIPS 2025Buffer layers for Test-Time Adaptation
147. NeurIPS 2025Class-aware Domain Knowledge Fusion and Fission for Continual Test-Time Adaptation
148. NeurIPS 2025Continuous Domain Generalization
149. NeurIPS 2025Controlled Visual Hallucination via Thalamus-Driven Decoupling Network for Domain Adaptation of Black-Box Predictors
150. NeurIPS 2025Correlated Low-Rank Adaptation for ConvNets

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。