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 187 篇，第 4 / 4 页

151. ICLR 2026Sparsity Forcing: Reinforcing Token Sparsity of MLLMs
152. ICLR 2026Sparsity-promoting Fine-tuning for Equivariant Materials Foundation Model
153. ICLR 2026Specialization after Generalization: Towards Understanding Test-Time Training in Foundation Models
154. ICLR 2026Speculative Speculative Decoding
155. ICLR 2026ssToken: Self-modulated and Semantic-aware Token Selection for LLM Fine-tuning
156. ICLR 2026Stable-LoRA: Stabilizing Feature Learning of Low-Rank Adaption
157. ICLR 2026StochasTok: Improving Fine-Grained Subword Understanding in LLMs
158. ICLR 2026Study of Training Dynamics for Memory-Constrained Fine-Tuning
159. ICLR 2026SumRA: Parameter Efficient Fine-tuning with Singular Value Decomposition and Summed Orthogonal Basis
160. ICLR 2026Sysformer: Safeguarding Frozen Large Language Models with Adaptive System Prompts
161. ICLR 2026Task-Adaptive Parameter-Efficient Fine-Tuning for Weather Foundation Models
162. ICLR 2026Task-Aware Data Selection via Proxy-Label Enhanced Distribution Matching for LLM Finetuning
163. ICLR 2026TerraFM: A Scalable Foundation Model for Unified Multisensor Earth Observation
164. ICLR 2026Test-Time Matching: Unlocking Compositional Reasoning in Multimodal Models
165. ICLR 2026The Forecast After the Forecast: A Post-Processing Shift in Time Series
166. ICLR 2026The Softmax Bottleneck Does Not Limit the Probabilities of the Most Likely Tokens
167. ICLR 2026Thompson Sampling via Fine-Tuning of LLMs
168. ICLR 2026Three Forward, One Backward: Memory-Efficient Full-Rank Fine-Tuning of Large Models via Extra Forward Passes
169. ICLR 2026Token-level Data Selection for Safe LLM Fine-tuning
170. ICLR 2026TokenSeek: Memory Efficient Fine Tuning via Instance-Aware Token Ditching
171. ICLR 2026TokMem: Tokenized Procedural Memory for Large Language Models
172. ICLR 2026Towards a Foundation Model for Crowdsourced Label Aggregation
173. ICLR 2026TRAC: Tensor-Train based Across-layer Compression for Parameter-Efficient Fine-Tuning
174. ICLR 2026Train-before-Test Harmonizes Language Model Rankings
175. ICLR 2026Training Large Language Models To Reason In Parallel With Global Forking Tokens
176. ICLR 2026Training-Free Loosely Speculative Decoding: Accepting Semantically Correct Drafts Beyond Exact Match
177. ICLR 2026Transducing Language Models
178. ICLR 2026TS$^2$: Training with Sparsemax+, Testing with Softmax for Accurate and Diverse LLM Fine-Tuning
179. ICLR 2026TSPulse: Tiny Pre-Trained Models with Disentangled Representations for Rapid Time-Series Analysis
180. ICLR 2026Type-Compliant Adaptation Cascades
181. ICLR 2026Uni-NTFM: A Unified Foundation Model for EEG Signal Representation Learning
182. ICLR 2026UniCA: Unified Covariate Adaptation for Time Series Foundation Model
183. ICLR 2026Universal Properties of Activation Sparsity in Modern Large Language Models
184. ICLR 2026VER: Vision Expert Transformer for Robot Learning via Foundation Distillation and Dynamic Routing
185. ICLR 2026Why Attention Patterns Exist: A Unifying Temporal Perspective Analysis
186. ICLR 2026Why Reinforcement Fine-Tuning Enables MLLMs Preserve Prior Knowledge Better: A Data Perspective
187. ICLR 2026Zero-Shot Adaptation of Behavioral Foundation Models to Unseen Dynamics

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。