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 404 篇，第 2 / 9 页

51. ICLR 2026Discrete Adjoint Matching
52. ICLR 2026Discrete Latent Features Ablate Adversarial Attack: A Robust Prompt Tuning Framework for VLMs
53. ICLR 2026Distilling to Hybrid Attention Models via KL-Guided Layer Selection
54. ICLR 2026DMAP: A Distribution Map for Text
55. ICLR 2026DND: Boosting Large Language Models with Dynamic Nested Depth
56. ICLR 2026E²LoRA: Efficient and Effective Low-Rank Adaptation with Entropy-Guided Adaptive Sharing
57. ICLR 2026Efficient Orthogonal Fine-Tuning with Principal Subspace Adaptation
58. ICLR 2026Embodied Navigation Foundation Model
59. ICLR 2026Enabling Fine-Tuning of Direct Feedback Alignment via Feedback-Weight Matching
60. ICLR 2026Escaping Policy Contraction: Contraction-Aware PPO (CaPPO) for Stable Language Model Fine-Tuning
61. ICLR 2026Explainable Token-level Noise Filtering for LLM Fine-tuning Datasets
62. ICLR 2026Exploring Interpretability for Visual Prompt Tuning with Cross-layer Concepts
63. ICLR 2026Exploring the Basin-Like Loss Landscape in Large Language Models
64. ICLR 2026Fine-Grained Activation Steering: Steering Less, Achieving More
65. ICLR 2026Fine-tuning Behavioral Cloning Policies with Preference‑Based Reinforcement Learning
66. ICLR 2026Fine-Tuning Diffusion Models via Intermediate Distribution Shaping
67. ICLR 2026Fine-tuning Done Right in Model Editing
68. ICLR 2026Fine-tuning Quantized Neural Networks with Zeroth-order Optimization
69. ICLR 2026FlexLoRA: Entropy-Guided Flexible Low-Rank Adaptation
70. ICLR 2026Flock: A Knowledge Graph Foundation Model via Learning on Random Walks
71. ICLR 2026FLoRG: Federated Fine-tuning with Low-rank Gram Matrices and Procrustes Alignment
72. ICLR 2026FM4NPP: A Scaling Foundation Model for Nuclear and Particle Physics
73. ICLR 2026FoNE: Precise Single-Token Number Embeddings via Fourier Features
74. ICLR 2026FZOO: Fast Zeroth-Order Optimizer for Fine‑Tuning Large Language Models towards Adam‑Scale Speed
75. ICLR 2026GIT-BO: High-Dimensional Bayesian Optimization with Tabular Foundation Models
76. ICLR 2026Gradient Intrinsic Dimensionality Alignment：Narrowing The Gap Between Low-Rank Adaptation and Full Fine-Tuning
77. ICLR 2026Gradient-Sign Masking for Task Vector Transport Across Pre-Trained Models
78. ICLR 2026GranViT: A Fine-Grained Vision Model With Autoregressive Perception For MLLMs
79. ICLR 2026Heterogeneous Federated Fine-Tuning with Parallel One-Rank Adaptation
80. ICLR 2026High Accuracy, Less Talk (HALT): Reliable LLMs through Capability-Aligned Finetuning
81. ICLR 2026Holdout-Loss-Based Data Selection for LLM Finetuning via In-Context Learning
82. ICLR 2026Homeostatic Adaptation of Optimal Population Codes under Metabolic Stress
83. ICLR 2026How Base Frequency Shapes RoPE: An Analytical Study of Frequency-Band Formation
84. ICLR 2026HYPER: A Foundation Model for Inductive Link Prediction with Knowledge Hypergraphs
85. ICLR 2026IA2: Alignment with ICL Activations improves Supervised Fine-Tuning
86. ICLR 2026IDEAL: Data Equilibrium Adaptation for Multi-Capability Language Model Alignment
87. ICLR 2026IGU-LoRA: Adaptive Rank Allocation via Integrated Gradients and Uncertainty-Aware Scoring
88. ICLR 2026Improving Block-Wise LLM Quantization by 4-bit Block-Wise Optimal Float (BOF4): Analysis and Variations
89. ICLR 2026IMSE: Intrinsic Mixture of Spectral Experts Fine-tuning for Test-Time Adaptation
90. ICLR 2026In-Context Learning of Temporal Point Processes with Foundation Inference Models
91. ICLR 2026Is Finer Better? The Limits of Microscaling Formats in Large Language Models
92. ICLR 2026Joint Adaptation of Uni-modal Foundation Models for Multi-modal Alzheimer's Disease Diagnosis
93. ICLR 2026KeepLoRA: Continual Learning with Residual Gradient Adaptation
94. ICLR 2026Learning What Reinforcement Learning Can't: Interleaved Online Fine-Tuning for Hardest Questions
95. ICLR 2026LinguaMap: Which Layers of LLMs Speak Your Language and How to Tune Them?
96. ICLR 2026LoFT: Low-Rank Adaptation That Behaves Like Full Fine-Tuning
97. ICLR 2026Log-Linear Attention
98. ICLR 2026Long-tailed Test-Time Adaptation for Vision-Language Models
99. ICLR 2026LoRA meets Riemannion: Muon Optimizer for Parametrization-independent Low-Rank Adapters
100. ICLR 2026LoRA-S: An Efficient Low Rank Adaptation scheme via Sylvester equation

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。