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 3 / 4 页

101. NeurIPS 2023Equivariant Adaptation of Large Pretrained Models
102. NeurIPS 2023Exact recovery and Bregman hard clustering of node-attributed Stochastic Block Model
103. NeurIPS 2023Fast Trainable Projection for Robust Fine-tuning
104. NeurIPS 2023Feature Adaptation for Sparse Linear Regression
105. NeurIPS 2023Fine-Grained Human Feedback Gives Better Rewards for Language Model Training
106. NeurIPS 2023FineMoGen: Fine-Grained Spatio-Temporal Motion Generation and Editing
107. NeurIPS 2023Foundation Model is Efficient Multimodal Multitask Model Selector
108. NeurIPS 2023Generalized Logit Adjustment: Calibrating Fine-tuned Models by Removing Label Bias in Foundation Models
109. NeurIPS 2023Generalized Semi-Supervised Learning via Self-Supervised Feature Adaptation
110. NeurIPS 2023Geodesic Multi-Modal Mixup for Robust Fine-Tuning
111. NeurIPS 2023Getting ViT in Shape: Scaling Laws for Compute-Optimal Model Design
112. NeurIPS 2023GPT4Tools: Teaching Large Language Model to Use Tools via Self-instruction
113. NeurIPS 2023HiBug: On Human-Interpretable Model Debug
114. NeurIPS 2023Holistic Transfer: Towards Non-Disruptive Fine-Tuning with Partial Target Data
115. NeurIPS 2023How to Fine-tune the Model: Unified Model Shift and Model Bias Policy Optimization
116. NeurIPS 2023HyenaDNA: Long-Range Genomic Sequence Modeling at Single Nucleotide Resolution
117. NeurIPS 2023Importance-aware Co-teaching for Offline Model-based Optimization
118. NeurIPS 2023Inner-Outer Aware Reconstruction Model for Monocular 3D Scene Reconstruction
119. NeurIPS 2023Interactive Multi-fidelity Learning for Cost-effective Adaptation of Language Model with Sparse Human Supervision
120. NeurIPS 2023Make Pre-trained Model Reversible: From Parameter to Memory Efficient Fine-Tuning
121. NeurIPS 2023Mixed Samples as Probes for Unsupervised Model Selection in Domain Adaptation
122. NeurIPS 2023MixFormerV2: Efficient Fully Transformer Tracking
123. NeurIPS 2023Mixture Weight Estimation and Model Prediction in Multi-source Multi-target Domain Adaptation
124. NeurIPS 2023Model Shapley: Equitable Model Valuation with Black-box Access
125. NeurIPS 2023Model Sparsity Can Simplify Machine Unlearning
126. NeurIPS 2023Model-enhanced Vector Index
127. NeurIPS 2023Moment Matching Denoising Gibbs Sampling
128. NeurIPS 2023MoVie: Visual Model-Based Policy Adaptation for View Generalization
129. NeurIPS 2023Near-Optimal $k$-Clustering in the Sliding Window Model
130. NeurIPS 2023On Sparse Modern Hopfield Model
131. NeurIPS 2023On the Connection between Pre-training Data Diversity and Fine-tuning Robustness
132. NeurIPS 2023Optimal Transport Model Distributional Robustness
133. NeurIPS 2023OV-PARTS: Towards Open-Vocabulary Part Segmentation
134. NeurIPS 2023Parameter-efficient Tuning of Large-scale Multimodal Foundation Model
135. NeurIPS 2023PIXIU: A Comprehensive Benchmark, Instruction Dataset and Large Language Model for Finance
136. NeurIPS 2023Preference-grounded Token-level Guidance for Language Model Fine-tuning
137. NeurIPS 2023R-divergence for Estimating Model-oriented Distribution Discrepancy
138. NeurIPS 2023RDumb: A simple approach that questions our progress in continual test-time adaptation
139. NeurIPS 2023Res-Tuning: A Flexible and Efficient Tuning Paradigm via Unbinding Tuner from Backbone
140. NeurIPS 2023Retaining Beneficial Information from Detrimental Data for Neural Network Repair
141. NeurIPS 2023Rewarded soups: towards Pareto-optimal alignment by interpolating weights fine-tuned on diverse rewards
142. NeurIPS 2023SegRefiner: Towards Model-Agnostic Segmentation Refinement with Discrete Diffusion Process
143. NeurIPS 2023Self-Chained Image-Language Model for Video Localization and Question Answering
144. NeurIPS 2023SPA: A Graph Spectral Alignment Perspective for Domain Adaptation
145. NeurIPS 2023Subspace Identification for Multi-Source Domain Adaptation
146. NeurIPS 2023Synthetic-to-Real Pose Estimation with Geometric Reconstruction
147. NeurIPS 2023Task-Robust Pre-Training for Worst-Case Downstream Adaptation
148. NeurIPS 2023The Goldilocks of Pragmatic Understanding: Fine-Tuning Strategy Matters for Implicature Resolution by LLMs
149. NeurIPS 2023TIES-Merging: Resolving Interference When Merging Models
150. NeurIPS 2023To Repeat or Not To Repeat: Insights from Scaling LLM under Token-Crisis

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。