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 531 篇，第 3 / 11 页

101. NeurIPS 2026Multimodal LLMs Outperform Pathology Foundation Models in Cross-Domain Histological Similarity
102. NeurIPS 2026NADS: Navigator-Guided Data Selection for Mitigating Catastrophic Forgetting in Fine-Tuning
103. NeurIPS 2026Neuro-KE: Knowledge-Guided Interfaces for Semantically Grounded EEG Foundation Models
104. NeurIPS 2026NeuroAtlas: Benchmarking Foundation Models for Clinical EEG and Brain-Computer Interfaces
105. NeurIPS 2026NeuroNTP - A Generalizable Multimodal Foundation Model for Epilepsy
106. NeurIPS 2026No One Knows the State-of-the-Art in Geospatial Foundation Models
107. NeurIPS 2026Nüwa.RNA: An RNA Foundation Model for Unified Representation with Deep Structure Infusion
108. NeurIPS 2026OATS: Online Data Augmentation for Time Series Foundation Models
109. NeurIPS 2026On the Design Space of Discrete Diffusion Online Adaptation for Molecular Optimization
110. NeurIPS 2026One Adapter For All: Towards Generalizable Many-To-One Domain Adaptation In Heterogeneous Collaborative Perception
111. NeurIPS 2026One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning
112. NeurIPS 2026One Language-Free Foundation Model Is Enough for Universal Vision Anomaly Detection
113. NeurIPS 2026One Loss to Rule Them All: Marked Time-to-Event for Structured EHR Foundation Models
114. NeurIPS 2026Online Change-point Detection using Foundation Probabilistic Forecasting Models
115. NeurIPS 2026OpenMHC: Accelerating the Science of Wearable Foundation Models
116. NeurIPS 2026Optimistic Q-value Adaptation for Offline-to-Online Reinforcement Learning
117. NeurIPS 2026OrbitLoRA: Learning Rotation-Aware Low-Data Adaptation of Vision Foundation Models
118. NeurIPS 2026PACZero: PAC-Private Fine-Tuning of Language Models via Sign Quantization
119. NeurIPS 2026Pan-FM: A Pan-Organ Foundation Model with Saliency-Guided Masking for Missing Robustness
120. NeurIPS 2026Personalized Safety in Federated Fine-Tuning of Large Language Models
121. NeurIPS 2026Position: The Road to Generalizable Neuro-Symbolic Learning Should be Paved with Foundation Models
122. NeurIPS 2026Pretraining Curricula Enable Selective Fine-tuning
123. NeurIPS 2026PriFT: Prior-Support Guided Token Reweighting for Supervised Fine-Tuning
124. NeurIPS 2026PriorVLA: Prior-Preserving Adaptation for Vision-Language-Action Models
125. NeurIPS 2026PRISM: Principal Subspace Alignment for Parameter-Efficient Fine-Tuning
126. NeurIPS 2026PROLA: Principal-Orthogonal Low-rank Adaptation for Predictive Spatiotemporal Weather Downscaling
127. NeurIPS 2026ProMo3D: Probing Motion Cues in Frozen 3D Foundation Models
128. NeurIPS 2026Prysma: Efficient Modality Adaptation for SLO-aware LLM-based Video Question Answering
129. NeurIPS 2026RAD-TFM: Robust and Domain-Adapted Tabular Foundation Models
130. NeurIPS 2026RadOmni: Advancing Foundation Model for Non-contrast CT with Omni Radiology Knowledge
131. NeurIPS 2026RAHF: Reward-Amplified Human Feedback for Closed-Loop Policy Fine-Tuning
132. NeurIPS 2026Raw-Routed Mixture of Adapters: A Causal Intervention for Routing Collapse in Time Series Foundation Models
133. NeurIPS 2026RayTun3R: Online Camera Adaptation in 3D Foundation Models
134. NeurIPS 2026Reasoning-Trace Collapse: Evaluating the Loss of Explicit Reasoning During Fine-Tuning
135. NeurIPS 2026Relation-Aware Graph Foundation Model
136. NeurIPS 2026Resource-Aware Parameter-Efficient Model Adaptation for Onboard High-Dimensional Data
137. NeurIPS 2026Rest-Tuning: Data-Efficient Adaptation of EEG Foundation Models to Individuals via Resting-State Signals
138. NeurIPS 2026Rethinking "RL Generalizes, SFT Memorizes": The Role of SFT Data
139. NeurIPS 2026Rethinking LLM Fine-Tuning via Weight Space Reparameterization: Preserving Safety during Downstream Adaptation
140. NeurIPS 2026RIZZ: Routing Interactions to Near Zero-Interference Zones for Continual Adaptation of Black-Box Agents
141. NeurIPS 2026Robust and Efficient Finetuning of Vision Foundation Models via Implicit Ensembling
142. NeurIPS 2026Robust Diffusion Models via Divergence-Induced Weighted Denoising
143. NeurIPS 2026SaMA: Morpho Adaptation via Asymmetric Expansion of Kronecker Product
144. NeurIPS 2026SapiensID 2.0: Aligning Human Recognition Foundation Models with Human Perception
145. NeurIPS 2026Scalable Adaptation of 3D Geometric Foundation Models via Weak Supervision from Internet Video
146. NeurIPS 2026Scalable Variational Bayesian Fine-Tuning of LLMs via Orthogonalized Low-Rank Adapters
147. NeurIPS 2026ScreenShot: A Foundation Model for Few-Shot Combination Drug Screening
148. NeurIPS 2026SDS-LoRA: Overcoming Anisotropic Gradient Scaling in Low-Rank Adaptation
149. NeurIPS 2026SLDR: Defending Against Malicious Fine-tuning via Selective Layers Recovery and Dynamic Routing
150. NeurIPS 2026Solver-as-Teacher: Solver-Guided On-Policy Post-Training Framework for PDE Foundation Models

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。