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 233 篇，第 3 / 5 页

101. CVPR 2025CustomKD: Customizing Large Vision Foundation for Edge Model Improvement via Knowledge Distillation
102. CVPR 2025DEFOM-Stereo: Depth Foundation Model Based Stereo Matching
103. CVPR 2025Distilling Monocular Foundation Model for Fine-grained Depth Completion
104. CVPR 2025Dynamic Group Normalization: Spatio-Temporal Adaptation to Evolving Data Statistics
105. CVPR 2025Efficient Transfer Learning for Video-language Foundation Models
106. CVPR 2025Everything to the Synthetic: Diffusion-driven Test-time Adaptation via Synthetic-Domain Alignment
107. CVPR 2025F^3OCUS - Federated Finetuning of Vision-Language Foundation Models with Optimal Client Layer Updating Strategy via Multi-objective Meta-Heuristics
108. CVPR 2025Faster Parameter-Efficient Tuning with Token Redundancy Reduction
109. CVPR 2025Feat2GS: Probing Visual Foundation Models with Gaussian Splatting
110. CVPR 2025Fine-Grained Erasure in Text-to-Image Diffusion-based Foundation Models
111. CVPR 2025FisherTune: Fisher-Guided Robust Tuning of Vision Foundation Models for Domain Generalized Segmentation
112. CVPR 2025FRAMES-VQA: Benchmarking Fine-Tuning Robustness across Multi-Modal Shifts in Visual Question Answering
113. CVPR 2025FSFM: A Generalizable Face Security Foundation Model via Self-Supervised Facial Representation Learning
114. CVPR 2025HyperFree: A Channel-adaptive and Tuning-free Foundation Model for Hyperspectral Remote Sensing Imagery
115. CVPR 2025Interpreting Object-level Foundation Models via Visual Precision Search
116. CVPR 2025Label Shift Meets Online Learning: Ensuring Consistent Adaptation with Universal Dynamic Regret
117. CVPR 2025Language-Assisted Debiasing and Smoothing for Foundation Model-Based Semi-Supervised Learning
118. CVPR 2025Lessons and Insights from a Unifying Study of Parameter-Efficient Fine-Tuning (PEFT) in Visual Recognition
119. CVPR 2025Lift3D Policy: Lifting 2D Foundation Models for Robust 3D Robotic Manipulation
120. CVPR 2025LoRA Recycle: Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs
121. CVPR 2025LoRACLR: Contrastive Adaptation for Customization of Diffusion Models
122. CVPR 2025Low-Rank Adaptation in Multilinear Operator Networks for Security-Preserving Incremental Learning
123. CVPR 2025Magma: A Foundation Model for Multimodal AI Agents
124. CVPR 2025Mamba as a Bridge: Where Vision Foundation Models Meet Vision Language Models for Domain-Generalized Semantic Segmentation
125. CVPR 2025Meta-Learning Hyperparameters for Parameter Efficient Fine-Tuning
126. CVPR 2025Minimal Interaction Seperated Tuning: A New Paradigm for Visual Adaptation
127. CVPR 2025MODfinity: Unsupervised Domain Adaptation with Multimodal Information Flow Intertwining
128. CVPR 2025MonoSplat: Generalizable 3D Gaussian Splatting from Monocular Depth Foundation Models
129. CVPR 2025OCRT: Boosting Foundation Models in the Open World with Object-Concept-Relation Triad
130. CVPR 2025Optimal Transport-Guided Source-Free Adaptation for Face Anti-Spoofing
131. CVPR 2025Parameter Efficient Mamba Tuning via Projector-targeted Diagonal-centric Linear Transformation
132. CVPR 2025Pioneering 4-Bit FP Quantization for Diffusion Models: Mixup-Sign Quantization and Timestep-Aware Fine-Tuning
133. CVPR 2025PointLoRA: Low-Rank Adaptation with Token Selection for Point Cloud Learning
134. CVPR 2025Post-pre-training for Modality Alignment in Vision-Language Foundation Models
135. CVPR 2025Project-Probe-Aggregate: Efficient Fine-Tuning for Group Robustness
136. CVPR 2025Rethinking Token Reduction with Parameter-Efficient Fine-Tuning in ViT for Pixel-Level Tasks
137. CVPR 2025Revisiting Source-Free Domain Adaptation: Insights into Representativeness, Generalization, and Variety
138. CVPR 2025Reward Fine-Tuning Two-Step Diffusion Models via Learning Differentiable Latent-Space Surrogate Reward
139. CVPR 2025RobSense: A Robust Multi-modal Foundation Model for Remote Sensing with Static, Temporal, and Incomplete Data Adaptability
140. CVPR 2025SapiensID: Foundation for Human Recognition
141. CVPR 2025SCAP: Transductive Test-Time Adaptation via Supportive Clique-based Attribute Prompting
142. CVPR 2025Sensitivity-Aware Efficient Fine-Tuning via Compact Dynamic-Rank Adaptation
143. CVPR 2025SketchFusion: Learning Universal Sketch Features through Fusing Foundation Models
144. CVPR 2025SoMA: Singular Value Decomposed Minor Components Adaptation for Domain Generalizable Representation Learning
145. CVPR 2025Tartan IMU: A Light Foundation Model for Inertial Positioning in Robotics
146. CVPR 2025Task-Specific Gradient Adaptation for Few-Shot One-Class Classification
147. CVPR 2025Thin-Shell-SfT: Fine-Grained Monocular Non-rigid 3D Surface Tracking with Neural Deformation Fields
148. CVPR 2025Towards More General Video-based Deepfake Detection through Facial Component Guided Adaptation for Foundation Model
149. CVPR 2025Universal Actions for Enhanced Embodied Foundation Models
150. CVPR 2025Unsupervised Foundation Model-Agnostic Slide-Level Representation Learning

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。