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 461 篇，第 3 / 10 页

101. ICLR 2025Fine-Tuning Attention Modules Only: Enhancing Weight Disentanglement in Task Arithmetic
102. ICLR 2025Fine-tuning can Help Detect Pretraining Data from Large Language Models
103. ICLR 2025Fine-tuning with Reserved Majority for Noise Reduction
104. ICLR 2025Forget the Data and Fine-Tuning! Just Fold the Network to Compress
105. ICLR 2025Fundamental Limitations on Subquadratic Alternatives to Transformers
106. ICLR 2025Fundamental Limits of Prompt Tuning Transformers: Universality, Capacity and Efficiency
107. ICLR 2025Generative Adapter: Contextualizing Language Models in Parameters with A Single Forward Pass
108. ICLR 2025Generative Representational Instruction Tuning
109. ICLR 2025GeoLoRA: Geometric integration for parameter efficient fine-tuning
110. ICLR 2025GOAL: A Generalist Combinatorial Optimization Agent Learner
111. ICLR 2025HiRA: Parameter-Efficient Hadamard High-Rank Adaptation for Large Language Models
112. ICLR 2025Hyper-Connections
113. ICLR 2025Inference-Aware Fine-Tuning for Best-of-N Sampling in Large Language Models
114. ICLR 2025Instruct-SkillMix: A Powerful Pipeline for LLM Instruction Tuning
115. ICLR 2025Intelligent Go-Explore: Standing on the Shoulders of Giant Foundation Models
116. ICLR 2025Intervening Anchor Token: Decoding Strategy in Alleviating Hallucinations for MLLMs
117. ICLR 2025Jamba: Hybrid Transformer-Mamba Language Models
118. ICLR 2025KaSA: Knowledge-Aware Singular-Value Adaptation of Large Language Models
119. ICLR 2025Knowledge Graph Finetuning Enhances Knowledge Manipulation in Large Language Models
120. ICLR 2025Kolmogorov-Arnold Transformer
121. ICLR 2025Large Convolutional Model Tuning via Filter Subspace
122. ICLR 2025Learning Diverse Attacks on Large Language Models for Robust Red-Teaming and Safety Tuning
123. ICLR 2025Learning to Adapt Frozen CLIP for Few-Shot Test-Time Domain Adaptation
124. ICLR 2025LiFT: Learning to Fine-Tune via Bayesian Parameter Efficient Meta Fine-Tuning
125. ICLR 2025LoCA: Location-Aware Cosine Adaptation for Parameter-Efficient Fine-Tuning
126. ICLR 2025LoLCATs: On Low-Rank Linearizing of Large Language Models
127. ICLR 2025LoR-VP: Low-Rank Visual Prompting for Efficient Vision Model Adaptation
128. ICLR 2025LoRA-Pro: Are Low-Rank Adapters Properly Optimized?
129. ICLR 2025LoRA-X: Bridging Foundation Models with Training-Free Cross-Model Adaptation
130. ICLR 2025LoRA3D: Low-Rank Self-Calibration of 3D Geometric Foundation models
131. ICLR 2025Lotus: Diffusion-based Visual Foundation Model for High-quality Dense Prediction
132. ICLR 2025Maintaining Structural Integrity in Parameter Spaces for Parameter Efficient Fine-tuning
133. ICLR 2025MallowsPO: Fine-Tune Your LLM with Preference Dispersions
134. ICLR 2025MambaPEFT: Exploring Parameter-Efficient Fine-Tuning for Mamba
135. ICLR 2025MambaQuant: Quantizing the Mamba Family with Variance Aligned Rotation Methods
136. ICLR 2025Matryoshka Multimodal Models
137. ICLR 2025Merging LoRAs like Playing LEGO: Pushing the Modularity of LoRA to Extremes Through Rank-Wise Clustering
138. ICLR 2025MeteoRA: Multiple-tasks Embedded LoRA for Large Language Models
139. ICLR 2025Mitigating Memorization in Language Models
140. ICLR 2025Mix-CPT: A Domain Adaptation Framework via Decoupling Knowledge Learning and Format Alignment
141. ICLR 2025Mix-LN: Unleashing the Power of Deeper Layers by Combining Pre-LN and Post-LN
142. ICLR 2025MM1.5: Methods, Analysis & Insights from Multimodal LLM Fine-tuning
143. ICLR 2025Model Equality Testing: Which Model is this API Serving?
144. ICLR 2025MoLEx: Mixture of Layer Experts for Fine-tuning with Sparse Upcycling
145. ICLR 2025Montessori-Instruct: Generate Influential Training Data Tailored for Student Learning
146. ICLR 2025MoS: Unleashing Parameter Efficiency of Low-Rank Adaptation with Mixture of Shards
147. ICLR 2025MTSAM: Multi-Task Fine-Tuning for Segment Anything Model
148. ICLR 2025Multiview Equivariance Improves 3D Correspondence Understanding with Minimal Feature Finetuning
149. ICLR 2025Neural ODE Transformers: Analyzing Internal Dynamics and Adaptive Fine-tuning
150. ICLR 2025Neural Phylogeny: Fine-Tuning Relationship Detection among Neural Networks

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。