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 1,492 篇，第 1 / 30 页

1. CVPR 20262D-LFM Lifting Foundation Model without 3D Supervision
2. CVPR 20263D-IDE 3D Implicit Depth Emergent
3. CVPR 2026Adapting a Pre-trained Single-Cell Foundation Model to Spatial Gene Expression
4. CVPR 2026Anatomical Domain Shifts Test-time Heterogeneous Adaptation for 3D Human Pose
5. CVPR 2026AnomalyVFM -- Transforming Vision Foundation Models into Zero-Shot Anomaly Detectors
6. CVPR 2026ArtHOI Taming Foundation Models for Monocular 4D Reconstruction of Hand-Articulated-Object
7. CVPR 2026AVA-Bench Atomic Visual Ability Benchmark for Vision Foundation Models
8. CVPR 2026Balanced Hierarchical Contrastive Learning with Decoupled Queries for Fine-grained Object
9. CVPR 2026Basis-Oriented Low-rank Transfer for Few-Shot and Test-Time Adaptation
10. CVPR 2026Beyond Graph Model Reliable VLM Fine-Tuning via Random Graph Adapter
11. CVPR 2026BiPA Bilevel Prompt Adaptation for Underwater Instance Segmentation
12. CVPR 2026Bootstrapping Video Semantic Segmentation Model via Distillation-assisted Test-Time Adaptation
13. CVPR 2026CASPA Graph-Structured Concept Anchors for Modality-Agnostic Adaptation in Vision-Language Models
14. CVPR 2026CD-Buffer Complementary Dual-Buffer Framework for Test-Time Adaptation in Adverse Weather
15. CVPR 2026CGL Advancing Continual GUI Learning via Reinforcement Fine-Tuning
16. CVPR 2026Chain-of-Models Pre-Training Rethinking Training Acceleration of Vision Foundation Models
17. CVPR 2026CHIPS Efficient CLIP Adaptation via Curvature-aware Hybrid Influence-based Data Selection
18. CVPR 2026CoFiDA-M Concept-Aware Feature Modulation for Cross-Domain Adaptation with Image-Only Inference
19. CVPR 2026Concept-Guided Fine-Tuning Steering ViTs away from Spurious Correlations to Improve
20. CVPR 2026CoVFT Context-aware Visual Fine-tuning for Multimodal Large Language Models
21. CVPR 2026CRAFT-LoRA Content-Style Personalization via Rank-Constrained Adaptation and Training-Free Fusion
22. CVPR 2026CrossEarth-Gate Fisher-Guided Adaptive Tuning Engine for Efficient Adaptation of Cross-Domain
23. CVPR 2026Cycle-Consistent Tuning for Layered Image Decomposition
24. CVPR 2026DeAR Fine-Grained VLM Adaptation by Decomposing Attention Head Roles
25. CVPR 2026Decoupled and Reusable Adaptation for Efficient Cross-Modal Transfer
26. CVPR 2026Decoupling Vision and Language Codebook Anchored Visual Adaptation
27. CVPR 2026Depth Any Panoramas A Foundation Model for Panoramic Depth Estimation
28. CVPR 2026DEVA Fine-tuning Multimodal Large Language Models for Visual Perception Tasks
29. CVPR 2026DGS Dual Gradient and Semantic-Shift Guided Low-Rank Adaptation for Class
30. CVPR 2026DiGraphHal-Bench Evaluating Multimodal Large Language Models on Complex Directed Graphs
31. CVPR 2026Emergent Extreme-View Geometry in 3D Foundation Models
32. CVPR 2026Fed-ADE Adaptive Learning Rate for Federated Post-adaptation under Distribution Shift
33. CVPR 2026Fine-Tuning Impairs the Balancedness of Foundation Models in Long-tailed Personalized
34. CVPR 2026FINER MLLMs Hallucinate under Fine-grained Negative Queries
35. CVPR 2026fMRI-LM Towards a Universal Foundation Model for Language-Aligned fMRI Understanding
36. CVPR 2026Foundation Encoders Are All You Need for Preference-Aware Personalization
37. CVPR 2026Foundation Model Priors Enhance Object Focus in Feature Space for
38. CVPR 2026FoundIR-v2 Optimizing Pre-Training Data Mixtures for Image Restoration Foundation Model
39. CVPR 2026Foundry Distilling 3D Foundation Models for the Edge
40. CVPR 2026Frame2Freq Spectral Adapters for Fine-Grained Video Understanding
41. CVPR 2026Generalizable Knowledge Distillation from Vision Foundation Models for Semantic Segmentation
42. CVPR 2026Generalized and Personalized Federated Learning with Black-Box Foundation Models via
43. CVPR 2026GeoBridge A Semantic-Anchored Multi-View Foundation Model Bridging Images and Text
44. CVPR 2026Harmonious Parameter Adaptation in Continual Visual Instruction Tuning for Safety-Aligned
45. CVPR 2026Harnessing the Power of Foundation Models for Accurate Material Classification
46. CVPR 2026Hidden Monotonicity Explaining Deep Neural Networks via their DC Decomposition
47. CVPR 2026HiDRA Hierarchical Degradation Representation and Adaptation with Generative Priors for
48. CVPR 2026HiLoRA Hierarchical Low-Rank Adaptation for Personalized Federated Learning
49. CVPR 2026How Much 3D Do Video Foundation Models Encode
50. CVPR 2026Immunizing Models Against Harmful Long-Horizon Fine-Tuning via Contractive Optimization Dynamics

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。