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 182 篇，第 1 / 4 页

1. NeurIPS 2026(Mis)generalization of Helpful-Only Fine-Tuning
2. NeurIPS 20263R-Adapter: Retrieval, Rewiring, and Refinement for Efficient Adaptation of 3D Reconstruction Model
3. NeurIPS 2026A Graph Foundation Model for Unified Clustering
4. NeurIPS 2026A low-rank decoder bottleneck bounds reliability in foundation-model perturbation prediction
5. NeurIPS 2026A unified pairwise distribution matching framework for graph domain adaptation under structure shift
6. NeurIPS 2026ABHBench: Evaluating Moral Decision-Making of Foundation Models from an Agentic Perspective
7. NeurIPS 2026AdaPreLoRA: Adafactor Preconditioned Low-Rank Adaptation
8. NeurIPS 2026Aligned LoRA Updates via Intrinsic Geometry for Federated Low-Rank Adaptation
9. NeurIPS 2026Aligning LLMs with Biomedical Knowledge using Balanced Fine-Tuning
10. NeurIPS 2026Alignment Dynamics in LLM Fine-Tuning
11. NeurIPS 2026AmbientFM: A Foundation Model for Ambient Sensing
12. NeurIPS 2026An Analytical Model of Compute-limited Multistage Training Pipelines
13. NeurIPS 2026An Open-Source Training Dataset for Foundation Models for Black-box Optimization
14. NeurIPS 2026AR1-ZO: Topology-Aware Rank-1 Zeroth-Order Queries for High-Rank LoRA Fine-Tuning
15. NeurIPS 2026Auditing Privacy Leakage in Tabular Foundation Model Embeddings
16. NeurIPS 2026B[FM]$^2$: Brain Foundation Model via Flow Matching with SplitUNet
17. NeurIPS 2026Barycentric Guidance: Turning Foundation Image Editors into Continuous Affective Controllers
18. NeurIPS 2026Behavioral Foundation Models for Quality Diversity
19. NeurIPS 2026Behavioral Geometric Supervision Aligns Video Foundation Models with Human Social Perception
20. NeurIPS 2026Benchmarking Fine-Grained Spatio-Temporal Awareness in Embodied Brain Models
21. NeurIPS 2026Beyond IID: How General Are Tabular Foundation Models, Really?
22. NeurIPS 2026Beyond LoRA vs. Full Fine-Tuning: Gradient-Guided Optimizer Routing for LLM Adaptation
23. NeurIPS 2026Beyond ViT Tokens: Masked-Diffusion Pretrained Convolutional Pathology Foundation Model for Cell-Level Dense Prediction
24. NeurIPS 2026BQ-LoRA: Binary-Quantized Low-Rank Adapters as Implicit Regularizers for Parameter-Efficient Fine-Tuning
25. NeurIPS 2026C2FT: Enhancing Fine-Grained Perception in MLLMs via Confuse-then-Contrast Fine-Tuning
26. NeurIPS 2026Calibrating Scientific Foundation Models with Inference-Time Stochastic Attention
27. NeurIPS 2026CanViT: Toward Active-Vision Foundation Models
28. NeurIPS 2026Certification-Enhanced Generalization Bounds
29. NeurIPS 2026ChildPose: Foundation for Children Pose Modeling
30. NeurIPS 2026CLEF: EEG Foundation Models for Learning Clinical Semantics
31. NeurIPS 2026Coarse-to-Fine 3D MRI Reconstruction via Resolution-Agnostic Neural Operators
32. NeurIPS 2026Communication-Efficient Personalized Adaptation via Federated-Local Model Merging
33. NeurIPS 2026Compact SO(3) Equivariant Atomistic Foundation Models via Structural Pruning
34. NeurIPS 2026Compute-Optimal Pretrain--Fine-tune in Ridge Gradient Flow
35. NeurIPS 2026CORA: Per-Slice Coherent Orthogonal Rotation for SVD-based Low-Rank Adaptation
36. NeurIPS 2026CORTEG: Foundation Models Enable Cross-Modality Representation Transfer from Scalp to Intracranial Brain Recordings
37. NeurIPS 2026CrafterDojo: A Suite of Foundation Models for Building Open-Ended Embodied Agents in Crafter
38. NeurIPS 2026DeepVoting: Learning and Improving Voting Rules with Fine-Tuning
39. NeurIPS 2026DEFT: Disentanglement-Enhanced Fine-Tuning for EEG Foundation Models
40. NeurIPS 2026Diffusion fine-tuning with Rewarded Moment Matching Distillation
41. NeurIPS 2026Diffusion Fine-Tuning: Iterative Refinement for Advanced Grounding with Diffusion Large Language Models
42. NeurIPS 2026Diffusion Meta-Prompting and Steering for Generalizable Foundation Model Adaptation
43. NeurIPS 2026Diffusion Tree Search for Inference Time Adaptation of Material Foundation Models
44. NeurIPS 2026Diffusion-DRF: Free, Rich, and Differentiable Reward for Video Diffusion Fine-Tuning
45. NeurIPS 2026Disentangling Homophilic and Heterophilic Patterns for Multi-Domain Graph Foundation Models
46. NeurIPS 2026Distillation of Foundation Models for Time-dependent PDEs
47. NeurIPS 2026Do Pathology Foundation Models Encode Disease Progression? A Pseudotime Analysis of Visual Representations
48. NeurIPS 2026Dominant-Layer ZO: A Single Layer Dominates Zeroth-Order Fine-Tuning of LLMs
49. NeurIPS 2026DRIVE: Fine-tuning via Data Contribution- and Diversity-aware Weighting with Prior Regularization
50. NeurIPS 2026Dual-Pronged LoRA: Achieving Near-Zero Forgetting and High-Performance Adaptation for MLLMs

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。