基础模型适配论文趋势 2023–2026

主要结论

• 基础模型适配论文从 2023 年的 159 篇增长到 2026 年的 602 篇，三年间扩大到约 3.8 倍。
• NeurIPS 是发基础模型适配论文最多的会议，2023–2026 年共 531 篇，占四个会议总量的 36%。
• 交叉方向里涨得最快的是深度学习 · foundation models：同时属于两个主题的论文从 2023 年的 7 篇增至 2026 年的 66 篇。
• 在「元学习与迁移」的 5 个主题里，它的 2026 年论文数排第 1；同组增长最快的持续学习是 1.7 倍，基础模型适配是 3.8 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 2026(Mis)generalization of Helpful-Only Fine-Tuning
• ICML 2026Active Learning with Foundation Model Priors: Efficient Learning under Class Imbalance
• ICLR 2026Benchmarking ECG Foundational Models: A Reality Check Across Clinical Tasks
• CVPR 2026CD-Buffer Complementary Dual-Buffer Framework for Test-Time Adaptation in Adverse Weather
• NeurIPS 2025An Investigation of Memorization Risk in Healthcare Foundation Models
• ICML 2025A Bayesian Model Selection Criterion for Selecting Pretraining Checkpoints
• ICLR 2025Better autoregressive regression with LLMs via regression-aware fine-tuning
• CVPR 20255%>100%: Breaking Performance Shackles of Full Fine-Tuning on Visual Recognition Tasks
• NeurIPS 2024Instruction Tuning Large Language Models to Understand Electronic Health Records
• ICML 2024By Tying Embeddings You Are Assuming the Distributional Hypothesis
• ICLR 2024A Hard-to-Beat Baseline for Training-free CLIP-based Adaptation
• CVPR 2024DePT: Decoupled Prompt Tuning
• NeurIPS 2023A Fast and Accurate Estimator for Large Scale Linear Model via Data Averaging
• ICML 2023Are Neurons Actually Collapsed? On the Fine-Grained Structure in Neural Representations
• ICLR 2023A Closer Look at Model Adaptation using Feature Distortion and Simplicity Bias
• CVPR 2023A-La-Carte Prompt Tuning (APT): Combining Distinct Data via Composable Prompting
• NeurIPS 2026A Graph Foundation Model for Unified Clustering
• ICML 2026AdaMeZO: Adam-style Zeroth-Order Optimizer for LLM Fine-tuning Without Maintaining the Moments
• ICLR 2026Bridging Radiology and Pathology Foundation Models via Concept-Based Multimodal Co-Adaptation
• CVPR 2026Fed-ADE Adaptive Learning Rate for Federated Post-adaptation under Distribution Shift

全部基础模型适配论文

共 159 篇，第 1 / 4 页

1. CVPR 2023A-La-Carte Prompt Tuning (APT): Combining Distinct Data via Composable Prompting
2. CVPR 2023Boosting Transductive Few-Shot Fine-Tuning With Margin-Based Uncertainty Weighting and Probability Regularization
3. CVPR 2023Divide and Adapt: Active Domain Adaptation via Customized Learning
4. CVPR 2023Fine-Grained Face Swapping via Regional GAN Inversion
5. CVPR 2023Foundation Model Drives Weakly Incremental Learning for Semantic Segmentation
6. CVPR 2023Guided Recommendation for Model Fine-Tuning
7. CVPR 2023Hint-Aug: Drawing Hints From Foundation Vision Transformers Towards Boosted Few-Shot Parameter-Efficient Tuning
8. CVPR 2023Integral Neural Networks
9. CVPR 2023Integrally Pre-Trained Transformer Pyramid Networks
10. CVPR 2023Masked Images Are Counterfactual Samples for Robust Fine-Tuning
11. CVPR 2023MELTR: Meta Loss Transformer for Learning To Fine-Tune Video Foundation Models
12. CVPR 2023MetaPortrait: Identity-Preserving Talking Head Generation With Fast Personalized Adaptation
13. CVPR 2023MHPL: Minimum Happy Points Learning for Active Source Free Domain Adaptation
14. CVPR 2023MOT: Masked Optimal Transport for Partial Domain Adaptation
15. CVPR 2023Neuro-Modulated Hebbian Learning for Fully Test-Time Adaptation
16. CVPR 2023Policy Adaptation From Foundation Model Feedback
17. CVPR 2023Prompt, Generate, Then Cache: Cascade of Foundation Models Makes Strong Few-Shot Learners
18. CVPR 2023Semi-Supervised Domain Adaptation With Source Label Adaptation
19. CVPR 2023Test Time Adaptation With Regularized Loss for Weakly Supervised Salient Object Detection
20. CVPR 2023Towards Better Stability and Adaptability: Improve Online Self-Training for Model Adaptation in Semantic Segmentation
21. CVPR 2023Towards Fast Adaptation of Pretrained Contrastive Models for Multi-Channel Video-Language Retrieval
22. CVPR 2023Train/Test-Time Adaptation With Retrieval
23. CVPR 2023Trainable Projected Gradient Method for Robust Fine-Tuning
24. CVPR 2023TWINS: A Fine-Tuning Framework for Improved Transferability of Adversarial Robustness and Generalization
25. ICLR 2023A Closer Look at Model Adaptation using Feature Distortion and Simplicity Bias
26. ICLR 2023Consolidator: Mergable Adapter with Group Connections for Visual Adaptation
27. ICLR 2023Dirichlet-based Uncertainty Calibration for Active Domain Adaptation
28. ICLR 2023Divide to Adapt: Mitigating Confirmation Bias for Domain Adaptation of Black-Box Predictors
29. ICLR 2023Energy-Based Test Sample Adaptation for Domain Generalization
30. ICLR 2023ESD: Expected Squared Difference as a Tuning-Free Trainable Calibration Measure
31. ICLR 2023Graph Domain Adaptation via Theory-Grounded Spectral Regularization
32. ICLR 2023Hyper-Decision Transformer for Efficient Online Policy Adaptation
33. ICLR 2023Interneurons accelerate learning dynamics in recurrent neural networks for statistical adaptation
34. ICLR 2023Lossless Adaptation of Pretrained Vision Models For Robotic Manipulation
35. ICLR 2023Preserving Pre-trained Features Helps Calibrate Fine-tuned Language Models
36. ICLR 2023Self-Distillation for Further Pre-training of Transformers
37. ICLR 2023Surgical Fine-Tuning Improves Adaptation to Distribution Shifts
38. ICLR 2023The Trade-off between Universality and Label Efficiency of Representations from Contrastive Learning
39. ICLR 2023Token Merging: Your ViT But Faster
40. ICLR 2023TVSPrune - Pruning Non-discriminative filters via Total Variation separability of intermediate representations without fine tuning
41. ICLR 2023Using Language to Extend to Unseen Domains
42. ICLR 2023When Source-Free Domain Adaptation Meets Learning with Noisy Labels
43. ICML 2023A Kernel-Based View of Language Model Fine-Tuning
44. ICML 2023AdaNPC: Exploring Non-Parametric Classifier for Test-Time Adaptation
45. ICML 2023Are Neurons Actually Collapsed? On the Fine-Grained Structure in Neural Representations
46. ICML 2023Bidirectional Adaptation for Robust Semi-Supervised Learning with Inconsistent Data Distributions
47. ICML 2023ClimaX: A foundation model for weather and climate
48. ICML 2023CocktailSGD: Fine-tuning Foundation Models over 500Mbps Networks
49. ICML 2023Conditional Tree Matching for Inference-Time Adaptation of Tree Prediction Models
50. ICML 2023Constant Matters: Fine-grained Error Bound on Differentially Private Continual Observation

常见问题

2023–2026 年四大会议一共有多少篇基础模型适配论文？

共 1,492 篇，按年份分别是 2023 年 159 篇、2024 年 270 篇、2025 年 461 篇、2026 年 602 篇。

NeurIPS 2026 有多少篇基础模型适配论文？

NeurIPS 2026 有 182 篇基础模型适配论文，上一届是 174 篇。

ICLR 2026 有多少篇基础模型适配论文？

ICLR 2026 有 187 篇基础模型适配论文，上一届是 149 篇。

ICML 2026 有多少篇基础模型适配论文？

ICML 2026 有 142 篇基础模型适配论文，上一届是 76 篇。

CVPR 2026 有多少篇基础模型适配论文？

CVPR 2026 有 91 篇基础模型适配论文，上一届是 62 篇。

哪个会议的基础模型适配论文最多？

NeurIPS，2023–2026 年共 531 篇。