基础模型适配论文趋势 2023–2026
微调与适配
统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 1,492 篇被归入该主题的论文。
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。
各会议论文数
按年份和会议统计
| 年份 | NeurIPS | ICLR | ICML | CVPR | 合计 |
|---|---|---|---|---|---|
| 2023 | 81 | 18 | 36 | 24 | 159 |
| 2024 | 94 | 50 | 70 | 56 | 270 |
| 2025 | 174 | 149 | 76 | 62 | 461 |
| 2026 | 182 | 187 | 142 | 91 | 602 |
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 233 篇，第 4 / 5 页
- CVPR 2025vesselFM: A Foundation Model for Universal 3D Blood Vessel Segmentation
- CVPR 2025Visual Persona: Foundation Model for Full-Body Human Customization
- CVPR 2025VladVA: Discriminative Fine-tuning of LVLMs
- CVPR 20243D-LFM: Lifting Foundation Model
- CVPR 2024A Pedestrian is Worth One Prompt: Towards Language Guidance Person Re-Identification
- CVPR 2024Adaptive Random Feature Regularization on Fine-tuning Deep Neural Networks
- CVPR 2024All in One Framework for Multimodal Re-identification in the Wild
- CVPR 2024AM-RADIO: Agglomerative Vision Foundation Model Reduce All Domains Into One
- CVPR 2024ASAM: Boosting Segment Anything Model with Adversarial Tuning
- CVPR 2024Asymmetric Masked Distillation for Pre-Training Small Foundation Models
- CVPR 2024BioCLIP: A Vision Foundation Model for the Tree of Life
- CVPR 2024Boosting Image Quality Assessment through Efficient Transformer Adaptation with Local Feature Enhancement
- CVPR 2024Boosting Order-Preserving and Transferability for Neural Architecture Search: a Joint Architecture Refined Search and Fine-tuning Approach
- CVPR 2024Bootstrapping SparseFormers from Vision Foundation Models
- CVPR 2024Bridging Remote Sensors with Multisensor Geospatial Foundation Models
- CVPR 2024Collaborating Foundation Models for Domain Generalized Semantic Segmentation
- CVPR 2024DePT: Decoupled Prompt Tuning
- CVPR 2024Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data
- CVPR 2024Efficient Stitchable Task Adaptation
- CVPR 2024Feature Re-Embedding: Towards Foundation Model-Level Performance in Computational Pathology
- CVPR 2024Federated Online Adaptation for Deep Stereo
- CVPR 2024FedSelect: Personalized Federated Learning with Customized Selection of Parameters for Fine-Tuning
- CVPR 2024Few-Shot Object Detection with Foundation Models
- CVPR 2024From-Ground-To-Objects: Coarse-to-Fine Self-supervised Monocular Depth Estimation of Dynamic Objects with Ground Contact Prior
- CVPR 2024General Object Foundation Model for Images and Videos at Scale
- CVPR 2024Gradient-based Parameter Selection for Efficient Fine-Tuning
- CVPR 2024Improved Self-Training for Test-Time Adaptation
- CVPR 2024Improving the Generalization of Segmentation Foundation Model under Distribution Shift via Weakly Supervised Adaptation
- CVPR 2024InfLoRA: Interference-Free Low-Rank Adaptation for Continual Learning
- CVPR 2024LEAD: Learning Decomposition for Source-free Universal Domain Adaptation
- CVPR 2024Learning CNN on ViT: A Hybrid Model to Explicitly Class-specific Boundaries for Domain Adaptation
- CVPR 2024Low-Rank Rescaled Vision Transformer Fine-Tuning: A Residual Design Approach
- CVPR 2024Low-Resource Vision Challenges for Foundation Models
- CVPR 2024MoML: Online Meta Adaptation for 3D Human Motion Prediction
- CVPR 2024OmniGlue: Generalizable Feature Matching with Foundation Model Guidance
- CVPR 2024One-Shot Open Affordance Learning with Foundation Models
- CVPR 2024OneTracker: Unifying Visual Object Tracking with Foundation Models and Efficient Tuning
- CVPR 2024Open-Vocabulary 3D Semantic Segmentation with Foundation Models
- CVPR 2024OpenEQA: Embodied Question Answering in the Era of Foundation Models
- CVPR 2024Orthogonal Adaptation for Modular Customization of Diffusion Models
- CVPR 2024Parameter Efficient Fine-tuning via Cross Block Orchestration for Segment Anything Model
- CVPR 2024Probing the 3D Awareness of Visual Foundation Models
- CVPR 2024Prompting Vision Foundation Models for Pathology Image Analysis
- CVPR 2024ProTeCt: Prompt Tuning for Taxonomic Open Set Classification
- CVPR 2024Q-Instruct: Improving Low-level Visual Abilities for Multi-modality Foundation Models
- CVPR 2024Rapid Motor Adaptation for Robotic Manipulator Arms
- CVPR 2024Representing Part-Whole Hierarchies in Foundation Models by Learning Localizability Composability and Decomposability from Anatomy via Self Supervision
- CVPR 2024S2MAE: A Spatial-Spectral Pretraining Foundation Model for Spectral Remote Sensing Data
- CVPR 2024Segment Any Event Streams via Weighted Adaptation of Pivotal Tokens
- CVPR 2024Semantically-Shifted Incremental Adapter-Tuning is A Continual ViTransformer
在 Claude、Cursor 里直接问这个趋势
接上 Paperlist MCP 后，写综述、挑方向或准备投稿时，不用离开对话框就能拿到这页的数字：每年各会议的论文数、增长倍数、涨得最快的子方向和代表论文，AI 会按你的问题整理。
可以直接复制这句话问 AI
用 paperlist 查基础模型适配在 NeurIPS 2023–2026 的论文趋势，哪一年涨得最快？
AI 会调用的工具：get_topic_stats {"topic": "foundation-model-adaptation"}
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。