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 5 / 7 页

  1. ICML 2025TabICL: A Tabular Foundation Model for In-Context Learning on Large Data
  2. ICML 2025TabPFN Unleashed: A Scalable and Effective Solution to Tabular Classification Problems
  3. ICML 2025Tackling Dimensional Collapse toward Comprehensive Universal Domain Adaptation
  4. ICML 2025Task-Agnostic Pre-training and Task-Guided Fine-tuning for Versatile Diffusion Planner
  5. ICML 2025Test-time Adaptation on Graphs via Adaptive Subgraph-based Selection and Regularized Prototypes
  6. ICML 2025Text-to-LoRA: Instant Transformer Adaption
  7. ICML 2025The Double-Ellipsoid Geometry of CLIP
  8. ICML 2025Theoretical Performance Guarantees for Partial Domain Adaptation via Partial Optimal Transport
  9. ICML 2025Token Cleaning: Fine-Grained Data Selection for LLM Supervised Fine-Tuning
  10. ICML 2025Towards Graph Foundation Models: Learning Generalities Across Graphs via Task-Trees
  11. ICML 2025Towards Understanding Fine-Tuning Mechanisms of LLMs via Circuit Analysis
  12. ICML 2025TreeLoRA: Efficient Continual Learning via Layer-Wise LoRAs Guided by a Hierarchical Gradient-Similarity Tree
  13. ICML 2025Understanding Overadaptation in Supervised Fine-Tuning: The Role of Ensemble Methods
  14. ICML 2025Upweighting Easy Samples in Fine-Tuning Mitigates Forgetting
  15. ICML 2025WeGeFT: Weight‑Generative Fine‑Tuning for Multi‑Faceted Efficient Adaptation of Large Models
  16. ICML 2025What Has a Foundation Model Found? Inductive Bias Reveals World Models
  17. ICML 2025When Can Proxies Improve the Sample Complexity of Preference Learning?
  18. ICML 2025Zero-Shot Adaptation of Parameter-Efficient Fine-Tuning in Diffusion Models
  19. ICML 2024A Closer Look at the Limitations of Instruction Tuning
  20. ICML 2024A decoder-only foundation model for time-series forecasting
  21. ICML 2024A Provably Effective Method for Pruning Experts in Fine-tuned Sparse Mixture-of-Experts
  22. ICML 2024Accelerating Transformer Pre-training with 2:4 Sparsity
  23. ICML 2024Active Label Correction for Semantic Segmentation with Foundation Models
  24. ICML 2024Asymmetry in Low-Rank Adapters of Foundation Models
  25. ICML 2024Batch Singular Value Polarization and Weighted Semantic Augmentation for Universal Domain Adaptation
  26. ICML 2024Bayesian Adaptation of Network Depth and Width for Continual Learning
  27. ICML 2024Bayesian Power Steering: An Effective Approach for Domain Adaptation of Diffusion Models
  28. ICML 2024By Tying Embeddings You Are Assuming the Distributional Hypothesis
  29. ICML 2024Compressible Dynamics in Deep Overparameterized Low-Rank Learning & Adaptation
  30. ICML 2024Connect Later: Improving Fine-tuning for Robustness with Targeted Augmentations
  31. ICML 2024Connecting the Dots: Collaborative Fine-tuning for Black-Box Vision-Language Models
  32. ICML 2024Covert Malicious Finetuning: Challenges in Safeguarding LLM Adaptation
  33. ICML 2024Data-Efficient Learning via Clustering-Based Sensitivity Sampling: Foundation Models and Beyond
  34. ICML 2024Debiased Offline Representation Learning for Fast Online Adaptation in Non-stationary Dynamics
  35. ICML 2024DeepPolar: Inventing Nonlinear Large-Kernel Polar Codes via Deep Learning
  36. ICML 2024Differentially Private Bias-Term Fine-tuning of Foundation Models
  37. ICML 2024Differentially Private Domain Adaptation with Theoretical Guarantees
  38. ICML 2024DoRA: Weight-Decomposed Low-Rank Adaptation
  39. ICML 2024DPZero: Private Fine-Tuning of Language Models without Backpropagation
  40. ICML 2024Erasing the Bias: Fine-Tuning Foundation Models for Semi-Supervised Learning
  41. ICML 2024ETHER: Efficient Finetuning of Large-Scale Models with Hyperplane Reflections
  42. ICML 2024Fine-grained Local Sensitivity Analysis of Standard Dot-Product Self-Attention
  43. ICML 2024Fine-tuning Reinforcement Learning Models is Secretly a Forgetting Mitigation Problem
  44. ICML 2024FlashST: A Simple and Universal Prompt-Tuning Framework for Traffic Prediction
  45. ICML 2024Foundation Policies with Hilbert Representations
  46. ICML 2024From Yes-Men to Truth-Tellers: Addressing Sycophancy in Large Language Models with Pinpoint Tuning
  47. ICML 2024Getting the most out of your tokenizer for pre-training and domain adaptation
  48. ICML 2024Gradual Divergence for Seamless Adaptation: A Novel Domain Incremental Learning Method
  49. ICML 2024Helpful or Harmful Data? Fine-tuning-free Shapley Attribution for Explaining Language Model Predictions
  50. ICML 2024LEVI: Generalizable Fine-tuning via Layer-wise Ensemble of Different Views

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