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 50 篇，第 1 / 1 页

1. ICLR 2024A Foundation Model for Error Correction Codes
2. ICLR 2024A Hard-to-Beat Baseline for Training-free CLIP-based Adaptation
3. ICLR 2024Adapting to Distribution Shift by Visual Domain Prompt Generation
4. ICLR 2024Advancing the Lower Bounds: an Accelerated, Stochastic, Second-order Method with Optimal Adaptation to Inexactness
5. ICLR 2024An Emulator for Fine-tuning Large Language Models using Small Language Models
6. ICLR 2024AutoLoRa: An Automated Robust Fine-Tuning Framework
7. ICLR 2024AutoVP: An Automated Visual Prompting Framework and Benchmark
8. ICLR 2024Batched Low-Rank Adaptation of Foundation Models
9. ICLR 2024Bayesian Low-rank Adaptation for Large Language Models
10. ICLR 2024BrainLM: A foundation model for brain activity recordings
11. ICLR 2024C-TPT: Calibrated Test-Time Prompt Tuning for Vision-Language Models via Text Feature Dispersion
12. ICLR 2024CLAP: Collaborative Adaptation for Patchwork Learning
13. ICLR 2024Convolution Meets LoRA: Parameter Efficient Finetuning for Segment Anything Model
14. ICLR 2024DePT: Decomposed Prompt Tuning for Parameter-Efficient Fine-tuning
15. ICLR 2024Differentially Private Synthetic Data via Foundation Model APIs 1: Images
16. ICLR 2024Directly Fine-Tuning Diffusion Models on Differentiable Rewards
17. ICLR 2024Dissecting Sample Hardness: A Fine-Grained Analysis of Hardness Characterization Methods for Data-Centric AI
18. ICLR 2024Dynamic Sparse No Training: Training-Free Fine-tuning for Sparse LLMs
19. ICLR 2024Enhancing Transferable Adversarial Attacks on Vision Transformers through Gradient Normalization Scaling and High-Frequency Adaptation
20. ICLR 2024Entropy is not Enough for Test-Time Adaptation: From the Perspective of Disentangled Factors
21. ICLR 2024Exploring the Common Appearance-Boundary Adaptation for Nighttime Optical Flow
22. ICLR 2024Fast Imitation via Behavior Foundation Models
23. ICLR 2024Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!
24. ICLR 2024Fine-Tuning Enhances Existing Mechanisms: A Case Study on Entity Tracking
25. ICLR 2024Fine-Tuning Language Models for Factuality
26. ICLR 2024Get more for less: Principled Data Selection for Warming Up Fine-Tuning in LLMs
27. ICLR 2024Gradual Domain Adaptation via Gradient Flow
28. ICLR 2024Increasing Model Capacity for Free: A Simple Strategy for Parameter Efficient Fine-tuning
29. ICLR 2024Mechanistically analyzing the effects of fine-tuning on procedurally defined tasks
30. ICLR 2024Memory-Assisted Sub-Prototype Mining for Universal Domain Adaptation
31. ICLR 2024Navigating Text-To-Image Customization: From LyCORIS Fine-Tuning to Model Evaluation
32. ICLR 2024Neural Fine-Tuning Search for Few-Shot Learning
33. ICLR 2024OVOR: OnePrompt with Virtual Outlier Regularization for Rehearsal-Free Class-Incremental Learning
34. ICLR 2024Pre-Training and Fine-Tuning Generative Flow Networks
35. ICLR 2024Principled Federated Domain Adaptation: Gradient Projection and Auto-Weighting
36. ICLR 2024Project and Probe: Sample-Efficient Adaptation by Interpolating Orthogonal Features
37. ICLR 2024QA-LoRA: Quantization-Aware Low-Rank Adaptation of Large Language Models
38. ICLR 2024Selective Mixup Fine-Tuning for Optimizing Non-Decomposable Objectives
39. ICLR 2024The False Promise of Imitating Proprietary Language Models
40. ICLR 2024Towards Few-Shot Adaptation of Foundation Models via Multitask Finetuning
41. ICLR 2024Towards Green AI in Fine-tuning Large Language Models via Adaptive Backpropagation
42. ICLR 2024Towards Robust and Efficient Cloud-Edge Elastic Model Adaptation via Selective Entropy Distillation
43. ICLR 2024Towards Seamless Adaptation of Pre-trained Models for Visual Place Recognition
44. ICLR 2024Two-stage LLM Fine-tuning with Less Specialization and More Generalization
45. ICLR 2024UniTabE: A Universal Pretraining Protocol for Tabular Foundation Model in Data Science
46. ICLR 2024VeRA: Vector-based Random Matrix Adaptation
47. ICLR 2024When Do Prompting and Prefix-Tuning Work? A Theory of Capabilities and Limitations
48. ICLR 2024WizardCoder: Empowering Code Large Language Models with Evol-Instruct
49. ICLR 2024WizardLM: Empowering Large Pre-Trained Language Models to Follow Complex Instructions
50. ICLR 2024Zero-Shot Robustification of Zero-Shot 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。