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 182 篇，第 4 / 4 页

151. NeurIPS 2026SPIRIT: Speed-Driven Online Adaptation for Self-Speculative Decoding
152. NeurIPS 2026Stability Regimes for Framing-Sensitive Fine-Tuning in Language Models
153. NeurIPS 2026Tabular Foundation Model for Generative Modelling
154. NeurIPS 2026TACO: Towards Task-Consistent Open-Vocabulary Adaptation in Video Recognition
155. NeurIPS 2026Tadpole: Autoencoders as Foundation Models for 3D PDEs with Online Learning
156. NeurIPS 2026The Geometry of Alignment Collapse: When Fine-Tuning Breaks Safety
157. NeurIPS 2026The Optimal Control Foundation of Early Exits – Turnpikes and ResNets
158. NeurIPS 2026The Surprising Effectiveness of Deleting Weights in LLM Reasoning and Adaptation
159. NeurIPS 2026Towards Identifying Dominant Low-Rank Subspaces in Zeroth-Order Fine-Tuning
160. NeurIPS 2026Towards Reconstructing Geographically Diverse Architecture with 3D Foundation Models
161. NeurIPS 2026Trainable Sparse Attention via Hybrid Top-k+Top-p Masking and Distillation Fine-Tuning
162. NeurIPS 2026Trust the Direction, Search the Step: Zero-and-First-Order Methods for LLM Fine-Tuning
163. NeurIPS 2026TS-ICL: A Flexible Time-Indexed Foundation Model for Time Series via In-Context Learning
164. NeurIPS 2026Tune-Up Open-Weight CLIP: Optimization Framework for Self-Supervised Fine-tuning of CLIP
165. NeurIPS 2026Tuning the Tuner
166. NeurIPS 2026U-MOF: Uncertainty-Guided Parameter-Efficient Multi-Objective Fine-Tuning for Long-Tailed Recognition
167. NeurIPS 2026Uncertainty-Aware Listwise Reinforcement Fine-Tuning for Fine-Grained Visual Classification
168. NeurIPS 2026Unified Panoramic Geometry Estimation via Multi-View Foundation Models
169. NeurIPS 2026Unveiling Implicit Advantage Symmetry: Why GRPO Struggles with Exploration and Difficulty Adaptation
170. NeurIPS 2026Vibe-Spike: An Energy-Preserving EEG Foundation Model Through the Landscape of Neural Coherence
171. NeurIPS 2026What DNA Foundation Models Learn Beyond Sequence Composition
172. NeurIPS 2026What do EEG Foundation Models Capture from Human Brain Signals?
173. NeurIPS 2026What Does an Observability Forecasting Foundation Model Know?
174. NeurIPS 2026What Drives Test-Time Adaptation for CLIP? A Controlled Empirical Study from an Update Perspective
175. NeurIPS 2026When Catastrophic Inheritance Meets Forgetting in Continual Adaptation of Foundation Models
176. NeurIPS 2026When does LeJEPA learn a World Model?
177. NeurIPS 2026When the Merge Coefficient Stops Mattering: Proximity Regularized Merging for Continual LoRA Adaptation
178. NeurIPS 2026When to Trust a PFN: Detecting Harmful Shift in Tabular Foundation Models
179. NeurIPS 2026Where Do We (Not) Need Temporal Context in Low-Resource Video Task Adaptation?
180. NeurIPS 2026Where You Backpropagate Matters: Token Hypothesis for Memory-Efficient Fine-Tuning
181. NeurIPS 2026Who Needs Labels? Adapting Vision Foundation Models With the Metadata You Already Have
182. NeurIPS 2026You CAN Teach an Old Model New Tricks: Domain Adaptation via Complementary Subspace Expansion

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。