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 324 篇，第 1 / 7 页

1. ICML 2026A Critical Look at Targeted Instruction Selection: Disentangling What Matters (and What Doesn’t)
2. ICML 2026A Language-Guided Bayesian Optimization for Efficient LoRA Hyperparameter Search
3. ICML 2026A Risk Decomposition Framework for Pre-hoc Fine-tuning Prediction
4. ICML 2026A Theory of How Pretraining Shapes Inductive Bias in Fine-Tuning
5. ICML 2026ACO-MoE-LoRA: Evolving-while-Training for Adapting Segment Anything Model 2 to Specialized Domains
6. ICML 2026Active Learning with Foundation Model Priors: Efficient Learning under Class Imbalance
7. ICML 2026AdaMeZO: Adam-style Zeroth-Order Optimizer for LLM Fine-tuning Without Maintaining the Moments
8. ICML 2026Adaptive Utilization of Low-Rank Adaptation via Conditioned Gating
9. ICML 2026AGZO: Activation-Guided Zeroth-Order Optimization for LLM Fine-Tuning
10. ICML 2026Annotations Mitigate Post-Training Mode Collapse
11. ICML 2026Are Common Substructures Transferable? Riemannian Graph Foundation Model with Neural Vector Bundles
12. ICML 2026AutoQRA: Joint Optimization of Mixed-Precision Quantization and Low-rank Adapters for Efficient LLM Fine-Tuning
13. ICML 2026Baguan-TS: dual in-context learning model for time series forecasting with covariates
14. ICML 2026Balanced LoRA: Removing Parameter Invariance to Accelerate Convergence
15. ICML 2026Bayesian-LoRA: Probabilistic Low-Rank Adaptation of Large Language Models
16. ICML 2026Beyond Log Likelihood: Probability-Based Objectives for Supervised Fine-Tuning across the Model Capability Continuum
17. ICML 2026Beyond Static Allocation: Dynamic Sensitivity-Aware Fine-Tuning for Vision Transformers
18. ICML 2026Beyond Temperature: Hyperfitting as a Late-Stage Geometric Expansion
19. ICML 2026BIOARC: Discovering Optimal Neural Architectures for Biological Foundation Models
20. ICML 2026Black-Box Assisted Regression: Phase Transitions and Minimax Optimality
21. ICML 2026CalM: A Self-Supervised Foundation Model for Population Dynamics in Calcium Imaging Data
22. ICML 2026Can Muon Fine-tune Adam-Pretrained Models?
23. ICML 2026Can We Build a Monolithic Model for Fake Image Detection? SICA: Semantic-Induced Constrained Adaptation for Unified-Yet-Discriminative Artifact Feature Space Reconstruction
24. ICML 2026Causal Fine-Tuning under Latent Confounded Shift
25. ICML 2026ChaosNexus: A Foundation Model for ODE-based Chaotic System Forecasting with Hierarchical Multi-scale Awareness
26. ICML 2026COBRA: Contribution-Based Bayesian Rank Allocation for Parameter-Efficient Fine-Tuning
27. ICML 2026CoLA: Cross-Modal Low-rank Adaptation for Multimodal Downstream Tasks
28. ICML 2026Collaborative and Efficient Fine-tuning: Leveraging Task Similarity
29. ICML 2026Compression as Adaptation: Implicit Visual Representation with Diffusion Foundation Models
30. ICML 2026ConFlux: Multivariate Time Series in Flux, One Unified Forecast in Confluence
31. ICML 2026Constrained Flow Optimization via Sequential Fine-Tuning for Molecular Design
32. ICML 2026Cross-Modal Knowledge Distillation without Paired Data: Theoretical Foundation and Algorithm
33. ICML 2026CSPLoRA: Confidence-Guided Structure Planning for Low-Rank Adaptation
34. ICML 2026Cure-SFT: Diagnostic-Guided Data Curation for Instruction Tuning
35. ICML 2026Data Difficulty and the Generalization–Extrapolation Tradeoff in LLM Fine-Tuning
36. ICML 2026Decoupled Low-Rank Adaptation for Robust Federated Fine-Tuning
37. ICML 2026Decoupled Training with Local Reinforcement Fine-Tuning in Federated Learning
38. ICML 2026DiP-G: Discrete Prompting for Graph Neural Networks
39. ICML 2026Distilling Linearized Behavior into Non-linear Fine-Tuning for Effective Task Arithmetic
40. ICML 2026Distribution Transformers: Fast Approximate Bayesian Inference With On-The-Fly Prior Adaptation
41. ICML 2026Diversity-aware Weight Perturbation Promotes Robust Adaptation
42. ICML 2026Don't Reinvent the Wheel, Just Realign the Spokes: Resource-Efficient Federated Fine-Tuning via Rank-Wise Expert Assembly
43. ICML 2026DTop-p MoE: Sparsity-Controlled Dynamic Top-p MoE for Foundation Model Pre-training
44. ICML 2026EDCO: Dynamic Curriculum Orchestration for Domain-specific Large Language Model Fine-tuning
45. ICML 2026EEG-FM-Bench: A Comprehensive Benchmark for the Systematic Evaluation and Diagnostic Analyses of EEG Foundation Models
46. ICML 2026EmBrace: A Collective Knowledge Fusion Framework Toward Unified EEG Foundation Models
47. ICML 2026End-to-End Compression for Tabular Foundation Models
48. ICML 2026Energy-Structured Low-Rank Adaptation for Continual Learning
49. ICML 2026Evolution Strategies at Scale: LLM Fine-Tuning Beyond Reinforcement Learning
50. ICML 2026FedHera: Towards Drift-Resilient Federated Fine-tuning with Heterogeneous Resources

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。