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 270 篇，第 3 / 6 页

101. ICLR 2024UniTabE: A Universal Pretraining Protocol for Tabular Foundation Model in Data Science
102. ICLR 2024VeRA: Vector-based Random Matrix Adaptation
103. ICLR 2024When Do Prompting and Prefix-Tuning Work? A Theory of Capabilities and Limitations
104. ICLR 2024WizardCoder: Empowering Code Large Language Models with Evol-Instruct
105. ICLR 2024WizardLM: Empowering Large Pre-Trained Language Models to Follow Complex Instructions
106. ICLR 2024Zero-Shot Robustification of Zero-Shot Models
107. ICML 2024A Closer Look at the Limitations of Instruction Tuning
108. ICML 2024A decoder-only foundation model for time-series forecasting
109. ICML 2024A Provably Effective Method for Pruning Experts in Fine-tuned Sparse Mixture-of-Experts
110. ICML 2024Accelerating Transformer Pre-training with 2:4 Sparsity
111. ICML 2024Active Label Correction for Semantic Segmentation with Foundation Models
112. ICML 2024Asymmetry in Low-Rank Adapters of Foundation Models
113. ICML 2024Batch Singular Value Polarization and Weighted Semantic Augmentation for Universal Domain Adaptation
114. ICML 2024Bayesian Adaptation of Network Depth and Width for Continual Learning
115. ICML 2024Bayesian Power Steering: An Effective Approach for Domain Adaptation of Diffusion Models
116. ICML 2024By Tying Embeddings You Are Assuming the Distributional Hypothesis
117. ICML 2024Compressible Dynamics in Deep Overparameterized Low-Rank Learning & Adaptation
118. ICML 2024Connect Later: Improving Fine-tuning for Robustness with Targeted Augmentations
119. ICML 2024Connecting the Dots: Collaborative Fine-tuning for Black-Box Vision-Language Models
120. ICML 2024Covert Malicious Finetuning: Challenges in Safeguarding LLM Adaptation
121. ICML 2024Data-Efficient Learning via Clustering-Based Sensitivity Sampling: Foundation Models and Beyond
122. ICML 2024Debiased Offline Representation Learning for Fast Online Adaptation in Non-stationary Dynamics
123. ICML 2024DeepPolar: Inventing Nonlinear Large-Kernel Polar Codes via Deep Learning
124. ICML 2024Differentially Private Bias-Term Fine-tuning of Foundation Models
125. ICML 2024Differentially Private Domain Adaptation with Theoretical Guarantees
126. ICML 2024DoRA: Weight-Decomposed Low-Rank Adaptation
127. ICML 2024DPZero: Private Fine-Tuning of Language Models without Backpropagation
128. ICML 2024Erasing the Bias: Fine-Tuning Foundation Models for Semi-Supervised Learning
129. ICML 2024ETHER: Efficient Finetuning of Large-Scale Models with Hyperplane Reflections
130. ICML 2024Fine-grained Local Sensitivity Analysis of Standard Dot-Product Self-Attention
131. ICML 2024Fine-tuning Reinforcement Learning Models is Secretly a Forgetting Mitigation Problem
132. ICML 2024FlashST: A Simple and Universal Prompt-Tuning Framework for Traffic Prediction
133. ICML 2024Foundation Policies with Hilbert Representations
134. ICML 2024From Yes-Men to Truth-Tellers: Addressing Sycophancy in Large Language Models with Pinpoint Tuning
135. ICML 2024Getting the most out of your tokenizer for pre-training and domain adaptation
136. ICML 2024Gradual Divergence for Seamless Adaptation: A Novel Domain Incremental Learning Method
137. ICML 2024Helpful or Harmful Data? Fine-tuning-free Shapley Attribution for Explaining Language Model Predictions
138. ICML 2024LEVI: Generalizable Fine-tuning via Layer-wise Ensemble of Different Views
139. ICML 2024Long Is More for Alignment: A Simple but Tough-to-Beat Baseline for Instruction Fine-Tuning
140. ICML 2024Long-Tail Learning with Foundation Model: Heavy Fine-Tuning Hurts
141. ICML 2024LoRA Training in the NTK Regime has No Spurious Local Minima
142. ICML 2024LoRA+: Efficient Low Rank Adaptation of Large Models
143. ICML 2024MOMENT: A Family of Open Time-series Foundation Models
144. ICML 2024Not all distributional shifts are equal: Fine-grained robust conformal inference
145. ICML 2024On Computational Limits of Modern Hopfield Models: A Fine-Grained Complexity Analysis
146. ICML 2024Open-Vocabulary Calibration for Fine-tuned CLIP
147. ICML 2024Parameter Efficient Quasi-Orthogonal Fine-Tuning via Givens Rotation
148. ICML 2024Parameter-Efficient Fine-Tuning with Controls
149. ICML 2024Parameter-Efficient Fine-Tuning with Discrete Fourier Transform
150. ICML 2024Position: Foundation Agents as the Paradigm Shift for Decision Making

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。