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 531 篇，第 2 / 11 页

51. NeurIPS 2026EEG-X: Toward Device-Agnostic and Noise-Robust Foundation Models for EEG
52. NeurIPS 2026Efficient Collaborative LLM Fine-Tuning over Heterogeneous Mobile Devices via Many Backbones to One Side-Network Tuning
53. NeurIPS 2026Efficient LLM Adaptation with Forward-Only Passes
54. NeurIPS 2026Efficiently Aligning Draft Models via Parameter- and Data-Efficient Adaptation
55. NeurIPS 2026Embedding Foundation Model Predictions in Discrete-Choice Models with Structural Guarantees
56. NeurIPS 2026Emergent Biological Capabilities in a Foundation Model for Molecular Interactions
57. NeurIPS 2026Enhancing Gaze Reasoning in Vision Foundation Models for Gaze Following
58. NeurIPS 2026ESSAM: A Novel Competitive Evolution Strategies Approach to Reinforcement Learning for Memory Efficient LLMs Fine-Tuning
59. NeurIPS 2026Estimating and Orthogonalizing Unknown Pre-training Gradients for Continual Fine-tuning of Large Language Models
60. NeurIPS 2026Evaluating Uncertainty Calibration in Probabilistic Time Series Foundation Models
61. NeurIPS 2026Evolution Fine-Tuning: Learning to Discover Across 371 Optimization Tasks
62. NeurIPS 2026Exploiting Fine-Tuning Structures to Improve Adversarial Transferability on Downstream SAM
63. NeurIPS 2026Extending Pretrained 10-Second ECG Foundation Models to Longer Horizons
64. NeurIPS 2026FedLoVA: Value-Only Aggregation for Federated LoRA Fine-Tuning of Large Language Models
65. NeurIPS 2026FedReCall: Recalling Client-Specific Directions in Federated LoRA Fine-tuning
66. NeurIPS 2026Fine-Grained Benchmark Generation for Comprehensive Evaluation of Foundation Models
67. NeurIPS 2026Fine-Tuning Improves Information Conveyance in Language Models
68. NeurIPS 2026Fine-tuning language encoding models on slow fMRI improves prediction for fast ECoG
69. NeurIPS 2026Fine-Tuning Language Models to Know What They Know
70. NeurIPS 2026FlatClip: Reusing Image Foundation Models for fMRI Representation Learning via Cortical Flatmaps
71. NeurIPS 2026FOCUS: Benchmarking Retinal Model Generalization from Foundation Vision Encoders to Multimodal LLMs
72. NeurIPS 2026FoldAbS: Repurposing the Protein Folding Model as a Foundation Encoder for Antibody Screening
73. NeurIPS 2026Follow the Mean: Reference-Guided Flow Matching
74. NeurIPS 2026Frank-LoRA: Federated Rank-Aware LoRA for Fine-Tuning Large Models
75. NeurIPS 2026From Next-Token to Next-Block: A Principled Adaptation Path for Diffusion LLMs
76. NeurIPS 2026Full Fine-Tuning Is Not the Problem: Why Adam Fails and SGD Succeeds in Few-Shot CLIP Adaptation
77. NeurIPS 2026GAPS: Gradient-Aware Adaptation-Gap Scoring for Time-Series Anomaly Detection with Foundation Models
78. NeurIPS 2026Glob3R: Global Structure-from-Motion with 3D Foundation Models
79. NeurIPS 2026GlucoFM: A Dual-Stream Foundation Model for Continuous Glucose Monitoring
80. NeurIPS 2026Guarding the Life Code: Preserving Membership Privacy in Genomic Foundation Models
81. NeurIPS 2026HandXFM: Semantic-Structural Distillation for Hand Radiograph Foundation Models
82. NeurIPS 2026High Performance Differentially Private Fine-Tuning using Dataset Distillation
83. NeurIPS 2026How Finite-Rank Bottleneck Shape the Low-Rank Adaptation Landscape
84. NeurIPS 2026How Much of a Model Do We Need? Redundancy and Slimmability in Remote Sensing Foundation Models
85. NeurIPS 2026Hybrid-LoRA: Bridging Full Fine-Tuning and Low-Rank Adaptation for Post-Training
86. NeurIPS 2026Hyperbolic Displacement-Constrained Adaptation for CLIP-Based Class-Incremental Learning
87. NeurIPS 2026ImmuVis: Hyperconvolutional Foundation Models for Imaging Mass Cytometry
88. NeurIPS 2026Inertia-1: An Open Exploration of Wearable Motion Foundation Models
89. NeurIPS 2026IRIS: Interpolative Rényi Iterative Self-play for Large Language Model Fine-Tuning
90. NeurIPS 2026Kairos: Toward Adaptive and Parameter-Efficient Time Series Foundation Models
91. NeurIPS 2026Language-Induced Priors for Domain Adaptation
92. NeurIPS 2026Latent Riemannian Flow Matching for Geometry-Grounded 3D Foundation Models
93. NeurIPS 2026LEAN: Library-Based Adaptation for Asynchronous, Federated Fine-Tuning
94. NeurIPS 2026Learning Rate Matters: Vanilla LoRA May Suffice for LLM Fine-tuning
95. NeurIPS 2026Lift, See, Act: Hierarchical Robot Policy Pretraining with 3D Foundation Models
96. NeurIPS 2026LOFT: Low-Rank Orthogonal Fine-Tuning via Task-Aware Support Selection
97. NeurIPS 2026Mask-Conditioned Gradient Masking for Fine-Tuning Mixture-of-Experts Diffusion Language Models
98. NeurIPS 2026MICE: Multi-animal Interaction Context Encoder — A Hierarchical Foundation Model for Mouse Behavior
99. NeurIPS 2026Monroe: A Molecular Foundation Model for In-context Probabilistic Inference
100. NeurIPS 2026Multimodal Foundation Agents Should Use Brain Data as Privileged Supervision

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。