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 3 / 30 页

101. ICLR 2026All-day Multi-scenes Lifelong Vision-and-Language Navigation with Tucker Adaptation
102. ICLR 2026Anchored Supervised Fine-Tuning
103. ICLR 2026Antibody: Strengthening Defense Against Harmful Fine-Tuning for Large Language Models via Attenuating Harmful Gradient Influence
104. ICLR 2026Any-Order Any-Subset AutoRegressive Model
105. ICLR 2026Arbitrary-Order Block SignSGD for Memory-Efficient LLM Fine-Tuning
106. ICLR 2026ARM-FM: Automated Reward Machines via Foundation Models for Compositional Reinforcement Learning
107. ICLR 2026Avey-B
108. ICLR 2026BA-LoRA: Bias-Alleviating Low-Rank Adaptation to Mitigate Catastrophic Inheritance in Large Language Models
109. ICLR 2026Bayesian Test-Time Adaptation via Dirichlet feature projection and GMM-Driven Inference for Motor Imagery EEG Decoding
110. ICLR 2026Be Careful When Fine-tuning On Open-Source LLMs: Your Fine-tuning Data Could Be Secretly Stolen!
111. ICLR 2026Benchmarking ECG Foundational Models: A Reality Check Across Clinical Tasks
112. ICLR 2026Beyond Accuracy: Are Time Series Foundation Models Well-Calibrated?
113. ICLR 2026BFM-Zero: A Promptable Behavioral Foundation Model for Humanoid Control Using Unsupervised Reinforcement Learning
114. ICLR 2026Bi-LoRA: Efficient Sharpness-Aware Minimization for Fine-Tuning Large-Scale Models
115. ICLR 2026Bilateral Information-aware Test-time Adaptation for Vision-Language Models
116. ICLR 2026BioCAP: Exploiting Synthetic Captions Beyond Labels in Biological Foundation Models
117. ICLR 2026Boomerang Distillation Enables Zero-Shot Model Size Interpolation
118. ICLR 2026BoRA: Towards More Expressive Low-Rank Adaptation with Block Diversity
119. ICLR 2026Brain-Semantoks: Learning Semantic Tokens of Brain Dynamics with a Self-Distilled Foundation Model
120. ICLR 2026Breaking Barriers: Do Reinforcement Fine-tuning Gains Transfer To Unseen Domains?
121. ICLR 2026Bridging Input Feature Spaces Towards Graph Foundation Models
122. ICLR 2026Bridging Radiology and Pathology Foundation Models via Concept-Based Multimodal Co-Adaptation
123. ICLR 2026CAR-LoRA: Training Compression-Aware and Robust LoRA Adapters for Evolving LLMs
124. ICLR 2026Cartridges: Lightweight and general-purpose long context representations via self-study
125. ICLR 2026Catching the Details: Self-Distilled RoI Predictors for Fine-Grained MLLM Perception
126. ICLR 2026CauKer: Classification Time Series Foundation Models Can Be Pretrained on Synthetic Data
127. ICLR 2026Cautious Optimizers: Improving Training with One Line of Code
128. ICLR 2026CerebraGloss: Instruction-Tuning a Large Vision-Language Model for Fine-Grained Clinical EEG Interpretation
129. ICLR 2026COLD-Steer: Steering Large Language Models via In-Context One-step Learning Dynamics
130. ICLR 2026CoMem: Compositional Concept-Graph Memory for Vision–Language Adaptation
131. ICLR 2026COMPACT: COMPositional Atomic-to-Complex Visual Capability Tuning
132. ICLR 2026Comparing the learning dynamics of in-context learning and fine-tuning in language models
133. ICLR 2026Complexity- and Statistics-Guided Anomaly Detection in Time Series Foundation Models
134. ICLR 2026CoRA: Boosting Time Series Foundation Models for Multivariate Forecasting through Correlation-aware Adapter
135. ICLR 2026CPiRi: Channel Permutation-Invariant Relational Interaction for Multivariate Time Series Forecasting
136. ICLR 2026CPQS-Tuning: A Model Self-Perception-Based Data Filtering Algorithm for Efficient Instruction Fine-Tuning
137. ICLR 2026Deep Hierarchical Learning with Nested Subspace Networks
138. ICLR 2026Deploying Models to Non-participating Clients in Federated Learning without Fine-tuning: A Hypernetwork-based Approach
139. ICLR 2026Developmental Federated Tuning: A Cognitive-Inspired Paradigm for Efficient LLM Adaptation
140. ICLR 2026DiaBlo: Diagonal Blocks Are Sufficient For Finetuning
141. ICLR 2026Differential Fine-Tuning Large Language Models Towards Better Diverse Reasoning Abilities
142. ICLR 2026Discrete Adjoint Matching
143. ICLR 2026Discrete Latent Features Ablate Adversarial Attack: A Robust Prompt Tuning Framework for VLMs
144. ICLR 2026Distilling to Hybrid Attention Models via KL-Guided Layer Selection
145. ICLR 2026DMAP: A Distribution Map for Text
146. ICLR 2026DND: Boosting Large Language Models with Dynamic Nested Depth
147. ICLR 2026E²LoRA: Efficient and Effective Low-Rank Adaptation with Entropy-Guided Adaptive Sharing
148. ICLR 2026Efficient Orthogonal Fine-Tuning with Principal Subspace Adaptation
149. ICLR 2026Embodied Navigation Foundation Model
150. ICLR 2026Enabling Fine-Tuning of Direct Feedback Alignment via Feedback-Weight Matching

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。