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 170 篇，第 2 / 4 页

51. ICML 2026Semi-Supervised Noise Adaptation: Transferring Knowledge from Noise Domain
52. ICML 2026Server-Proximal Aggregation for Federated Domain-Incremental Learning under Partial Participation: Task-Uniform Convergence and Backward Transfer
53. ICML 2026Sobolev Regularized Score Difference Estimation in Diffusion Models
54. ICML 2026Spike Camera Autofocus via Frequency-Domain Spectral-Centroid Migration
55. ICML 2026Stabilizing In-Context Multi-Source Domain Adaptation for Biomedical Images Through Controls
56. ICML 2026SURGE: Surrogate Gradient Adaptation in Binary Neural Networks
57. ICML 2026SyMerge: From Non-Interference to Synergistic Merging via Single-Layer Adaptation
58. ICML 2026TiME: Test-Time Mixture-of-Experts Routing via Asymmetric CO-Optimal Transport for Continual Test-Time Adaptation
59. ICML 2026Transport or Discard: Robust Unbalanced Optimal Transport for Cross-Domain Policy Adaptation
60. ICML 2026Turning Adaptation into Assets: Cross-Domain Bridging for Online Vision-Language Navigation
61. ICML 2026U$^3$CF: Unbiased, Unconfounding, and Unified Causal Framework for Multi-Target Domain Adaptation
62. ICML 2026Unifying Value Alignment and Assignment in Cross-Domain Offline Reinforcement Learning with Heterogeneous Datasets
63. ICML 2026Updating Parametric Knowledge with Context Distillation Retains Post-Training Capabilities
64. ICML 2026Variational Adapter for Cross-modal Similarity Representation
65. ICML 2026Variational Learning of Disentangled Representations
66. ICML 2026Walrus: A Cross-domain Foundation Model for Continuum Dynamics
67. ICML 2026What Makes a Strong Model? A Unified Spectral Analysis of Knowledge Transfer over High-dimensional Linear Regression
68. ICML 2026When Do Graph Foundation Models Transfer? A Data-Centric Theory
69. ICML 2026When More Data Doesn't Help: Limits of Adaptation in Multitask Learning
70. ICML 2025A Closer Look at Multimodal Representation Collapse
71. ICML 2025A General Representation-Based Approach to Multi-Source Domain Adaptation
72. ICML 2025Adapter Naturally Serves as Decoupler for Cross-Domain Few-Shot Semantic Segmentation
73. ICML 2025Addressing Imbalanced Domain-Incremental Learning through Dual-Balance Collaborative Experts
74. ICML 2025Balanced Learning for Domain Adaptive Semantic Segmentation
75. ICML 2025Beyond Entropy: Region Confidence Proxy for Wild Test-Time Adaptation
76. ICML 2025Come Together, But Not Right Now: A Progressive Strategy to Boost Low-Rank Adaptation
77. ICML 2025Componential Prompt-Knowledge Alignment for Domain Incremental Learning
78. ICML 2025Concept-Based Unsupervised Domain Adaptation
79. ICML 2025COSDA: Counterfactual-based Susceptibility Risk Framework for Open-Set Domain Adaptation
80. ICML 2025Disentangled Graph Spectral Domain Adaptation
81. ICML 2025DPCore: Dynamic Prompt Coreset for Continual Test-Time Adaptation
82. ICML 2025ExPLoRA: Parameter-Efficient Extended Pre-Training to Adapt Vision Transformers under Domain Shifts
83. ICML 2025FedPHA: Federated Prompt Learning for Heterogeneous Client Adaptation
84. ICML 2025Flowing Datasets with Wasserstein over Wasserstein Gradient Flows
85. ICML 2025Function Encoders: A Principled Approach to Transfer Learning in Hilbert Spaces
86. ICML 2025GCAL: Adapting Graph Models to Evolving Domain Shifts
87. ICML 2025Generalizable Multi-Camera 3D Object Detection from a Single Source via Fourier Cross-View Learning
88. ICML 2025GS-Bias: Global-Spatial Bias Learner for Single-Image Test-Time Adaptation of Vision-Language Models
89. ICML 2025Heterogeneous Label Shift: Theory and Algorithm
90. ICML 2025Homophily Enhanced Graph Domain Adaptation
91. ICML 2025How Much Can Transfer? BRIDGE: Bounded Multi-Domain Graph Foundation Model with Generalization Guarantees
92. ICML 2025MaskTwins: Dual-form Complementary Masking for Domain-Adaptive Image Segmentation
93. ICML 2025Merge-Friendly Post-Training Quantization for Multi-Target Domain Adaptation
94. ICML 2025Multi-Domain Graph Foundation Models: Robust Knowledge Transfer via Topology Alignment
95. ICML 2025Mutual Learning for SAM Adaptation: A Dual Collaborative Network Framework for Source-Free Domain Transfer
96. ICML 2025Neutral residues: revisiting adapters for model extension
97. ICML 2025Optimal Transfer Learning for Missing Not-at-Random Matrix Completion
98. ICML 2025QT-DoG: Quantization-Aware Training for Domain Generalization
99. ICML 2025Random Registers for Cross-Domain Few-Shot Learning
100. ICML 2025Revisiting Continuity of Image Tokens for Cross-domain Few-shot Learning

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。