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 76 篇，第 2 / 2 页

51. ICML 2025SAM2Act: Integrating Visual Foundation Model with A Memory Architecture for Robotic Manipulation
52. ICML 2025SAN: Hypothesizing Long-Term Synaptic Development and Neural Engram Mechanism in Scalable Model's Parameter-Efficient Fine-Tuning
53. ICML 2025Scaling Laws for Forgetting during Finetuning with Pretraining Data Injection
54. ICML 2025SeedLoRA: A Fusion Approach to Efficient LLM Fine-Tuning
55. ICML 2025Sketch to Adapt: Fine-Tunable Sketches for Efficient LLM Adaptation
56. ICML 2025SPACE: Your Genomic Profile Predictor is a Powerful DNA Foundation Model
57. ICML 2025SparseLoRA: Accelerating LLM Fine-Tuning with Contextual Sparsity
58. ICML 2025SToFM: a Multi-scale Foundation Model for Spatial Transcriptomics
59. ICML 2025TabICL: A Tabular Foundation Model for In-Context Learning on Large Data
60. ICML 2025TabPFN Unleashed: A Scalable and Effective Solution to Tabular Classification Problems
61. ICML 2025Tackling Dimensional Collapse toward Comprehensive Universal Domain Adaptation
62. ICML 2025Task-Agnostic Pre-training and Task-Guided Fine-tuning for Versatile Diffusion Planner
63. ICML 2025Test-time Adaptation on Graphs via Adaptive Subgraph-based Selection and Regularized Prototypes
64. ICML 2025Text-to-LoRA: Instant Transformer Adaption
65. ICML 2025The Double-Ellipsoid Geometry of CLIP
66. ICML 2025Theoretical Performance Guarantees for Partial Domain Adaptation via Partial Optimal Transport
67. ICML 2025Token Cleaning: Fine-Grained Data Selection for LLM Supervised Fine-Tuning
68. ICML 2025Towards Graph Foundation Models: Learning Generalities Across Graphs via Task-Trees
69. ICML 2025Towards Understanding Fine-Tuning Mechanisms of LLMs via Circuit Analysis
70. ICML 2025TreeLoRA: Efficient Continual Learning via Layer-Wise LoRAs Guided by a Hierarchical Gradient-Similarity Tree
71. ICML 2025Understanding Overadaptation in Supervised Fine-Tuning: The Role of Ensemble Methods
72. ICML 2025Upweighting Easy Samples in Fine-Tuning Mitigates Forgetting
73. ICML 2025WeGeFT: Weight‑Generative Fine‑Tuning for Multi‑Faceted Efficient Adaptation of Large Models
74. ICML 2025What Has a Foundation Model Found? Inductive Bias Reveals World Models
75. ICML 2025When Can Proxies Improve the Sample Complexity of Preference Learning?
76. ICML 2025Zero-Shot Adaptation of Parameter-Efficient Fine-Tuning in Diffusion 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。