基础模型适配论文趋势 2023–2026

微调与适配

统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 1,492 篇被归入该主题的论文。

主要结论

每年论文数

各会议论文数

按年份和会议统计

基础模型适配论文数，按年份和会议
年份NeurIPSICLRICMLCVPR合计
202381183624159
202494507056270
20251741497662461
202618218714291602

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

全部基础模型适配论文

年份全部2023202420252026
会议全部NeurIPSICLRICMLCVPR

共 324 篇，第 2 / 7 页

  1. ICML 2026FedPissa: Towards Federated Personalized Adaptation of Foundation Models via LoRA Subspace Mapping
  2. ICML 2026FedTreeLoRA: Reconciling Statistical and Functional Heterogeneity in Federated LoRA Fine-Tuning
  3. ICML 2026Fine-Tuning of Transformer models with Frames
  4. ICML 2026Fine-Tuning Without Forgetting In-Context Learning: A Theoretical Analysis of Linear Attention Models
  5. ICML 2026Fingerprinting Pre-trained Encoders under Arbitrary Downstream Fine-Tuning via Adversarial Shifting
  6. ICML 2026FIRE: Multi-Fidelity Regression with Distribution-Conditioned In-Context Learning Using Tabular Foundation Models
  7. ICML 2026FiX: Introducing Fine-grained Forget Gate into Softmax Attention
  8. ICML 2026Foundation Inference Models for Ordinary Differential Equations
  9. ICML 2026From Static Constraints to Dynamic Adaptation: Sample-Level Constraint Relaxation for Offline-to-Online Reinforcement Learning
  10. ICML 2026Geometry-Preserving Orthonormal Initialization for Low-Rank Adaptation in RLVR
  11. ICML 2026GFMate: Empowering Graph Foundation Models with Test-time Prompt Tuning
  12. ICML 2026GOTabPFN: From Feature Ordering to Compact Tokenization for Tabular Foundation Models on High-Dimensional Data
  13. ICML 2026GPan-LoRA: Gaussian Process Amortized Networks for Bayesian Low-Rank Adaptation in Large Language Models
  14. ICML 2026GR-LoRA: Gradient-Recycling Low-Rank Adaptation for Class-Incremental Learning
  15. ICML 2026Hierarchical Causal Abduction: A Foundation Framework for Explainable Model Predictive Control
  16. ICML 2026ICR-RL: Deep Reinforcement Learning via In-Context-Regression
  17. ICML 2026iLoRA: Bayesian Low-Rank Adaptation with Latent Interaction Graphs for Microbiome Diagnosis
  18. ICML 2026Is One Layer Enough? Understanding Inference Dynamics in Tabular Foundation Models
  19. ICML 2026JANUS-LORA: A Balanced Low-Rank Adaptation for Continual Learning
  20. ICML 2026KromHC: Manifold-Constrained Hyper-Connections with Kronecker-Product Residual Matrices
  21. ICML 2026Learning a Zeroth-Order Optimizer for Fine-Tuning LLMs
  22. ICML 2026Learning Graph Foundation Models on Riemannian Graph-of-Graphs
  23. ICML 2026Learning in the Fisher Subspace: A Guided Initialization for LoRA Fine-Tuning
  24. ICML 2026LimiX-2M: Mitigating Low-Rank Collapse and Attention Bottlenecks in Tabular Foundation Models
  25. ICML 2026Low Kruskal-Rank Adaptation
  26. ICML 2026LOZO+: Provably Efficient Zeroth-Order Fine-Tuning via Greedy Low-Rank Subspace Selection
  27. ICML 2026Mantis: Lightweight Foundation Model for Time Series Classification
  28. ICML 2026MDGMIX: Boundary-Aware Subgraph Mixing for Multi-Domain Graph Pre-Training
  29. ICML 2026Message Tuning Outshines Graph Prompt Tuning: A Prismatic Space Perspective
  30. ICML 2026MetaPerch: Learning from metadata for bioacoustics foundation models
  31. ICML 2026Midtraining Bridges Pretraining and Posttraining Distributions
  32. ICML 2026MODEL SOUPS NEED ONLY ONE INGREDIENT
  33. ICML 2026Multi-Label Test-Time Adaptation with Bayesian Conditional Priors
  34. ICML 2026MultiLoReFT: Decoupling Shared and Modality-Specific Subspaces in Multimodal Learning via Low-Rank Representation Fine-Tuning
  35. ICML 2026NeuroCLUS: A Foundation Model with Functional Clustering for Intracranial Neural Decoding
  36. ICML 2026No Need to Train Your RDB Foundation Model
  37. ICML 2026Olivia: Harmonizing Time Series Foundation Models with Power Spectral Density
  38. ICML 2026Omni-fMRI: A Universal Atlas-Free fMRI Foundation Model
  39. ICML 2026On the Entropy Dynamics in Reinforcement Fine-Tuning of Large Language Models
  40. ICML 2026Origo: Interpretable Multi-physics PDE Foundation Model through Neural Operator Splitting
  41. ICML 2026PATCHCODE: Discrete Latent Predictive Learning for EEG Foundation Model
  42. ICML 2026PFT: Phonon Fine-tuning for Machine Learned Interatomic Potentials
  43. ICML 2026PISA: Privacy-Preserving Split Adaptation with Model IP Protection
  44. ICML 2026PixCLIP: Towards Fine-grained Vision-Language Understanding via Any-granularity Pixel-Text Alignment
  45. ICML 2026PLATE: Plasticity-Tunable Efficient Adapters for Geometry-Aware Continual Learning
  46. ICML 2026PLoRA: Efficient Concurrent LoRA Training for Large Language Models
  47. ICML 2026Preference Goal Tuning: Post-Training as Latent Control for Frozen Policies
  48. ICML 2026Progressive Graph Structure Adjustment for Homophily Shift Adaptation
  49. ICML 2026Quantifying the Uncertainty of Foundation Models with Singular Value Ensembles
  50. ICML 2026Residual-Guided Multi-Resolution Refinement of Foundation Models: A Case Study in Drought Forecasting

在 Claude、Cursor 里直接问这个趋势

接上 Paperlist MCP 后，写综述、挑方向或准备投稿时，不用离开对话框就能拿到这页的数字：每年各会议的论文数、增长倍数、涨得最快的子方向和代表论文，AI 会按你的问题整理。

可以直接复制这句话问 AI

用 paperlist 查基础模型适配在 NeurIPS 2023–2026 的论文趋势，哪一年涨得最快？

AI 会调用的工具：get_topic_stats {"topic": "foundation-model-adaptation"}

两分钟接入 Paperlist MCP（Claude Code、Cursor、Codex、ChatGPT）

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。

「元学习与迁移」下的其他主题