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 1,492 篇，第 29 / 30 页

  1. ICML 2023mPLUG-2: A Modularized Multi-modal Foundation Model Across Text, Image and Video
  2. ICML 2023On the Power of Foundation Models
  3. ICML 2023On the Role of Attention in Prompt-tuning
  4. ICML 2023Random Classification Noise does not defeat All Convex Potential Boosters Irrespective of Model Choice
  5. ICML 2023RLSbench: Domain Adaptation Under Relaxed Label Shift
  6. ICML 2023SinDDM: A Single Image Denoising Diffusion Model
  7. ICML 2023Structural Re-weighting Improves Graph Domain Adaptation
  8. ICML 2023Target-Aware Generative Augmentations for Single-Shot Adaptation
  9. ICML 2023Task-Specific Skill Localization in Fine-tuned Language Models
  10. ICML 2023Taxonomy-Structured Domain Adaptation
  11. ICML 2023Test-time Adaptation with Slot-Centric Models
  12. NeurIPS 2023A Fast and Accurate Estimator for Large Scale Linear Model via Data Averaging
  13. NeurIPS 2023A Simple Yet Effective Strategy to Robustify the Meta Learning Paradigm
  14. NeurIPS 2023AdaVAE: Bayesian Structural Adaptation for Variational Autoencoders
  15. NeurIPS 2023BayesTune: Bayesian Sparse Deep Model Fine-tuning
  16. NeurIPS 2023Benchmarking Foundation Models with Language-Model-as-an-Examiner
  17. NeurIPS 2023Benchmarking Robustness of Adaptation Methods on Pre-trained Vision-Language Models
  18. NeurIPS 2023Beyond Invariance: Test-Time Label-Shift Adaptation for Addressing "Spurious" Correlations
  19. NeurIPS 2023Brant: Foundation Model for Intracranial Neural Signal
  20. NeurIPS 2023Chasing Fairness Under Distribution Shift: A Model Weight Perturbation Approach
  21. NeurIPS 2023Combinatorial Optimization with Policy Adaptation using Latent Space Search
  22. NeurIPS 2023Composing Parameter-Efficient Modules with Arithmetic Operation
  23. NeurIPS 2023Concept Distillation: Leveraging Human-Centered Explanations for Model Improvement
  24. NeurIPS 2023Context-guided Embedding Adaptation for Effective Topic Modeling in Low-Resource Regimes
  25. NeurIPS 2023Counting Distinct Elements in the Turnstile Model with Differential Privacy under Continual Observation
  26. NeurIPS 2023Customizable Image Synthesis with Multiple Subjects
  27. NeurIPS 2023Data Portraits: Recording Foundation Model Training Data
  28. NeurIPS 2023Data Selection for Language Models via Importance Resampling
  29. NeurIPS 2023Demographic Parity Constrained Minimax Optimal Regression under Linear Model
  30. NeurIPS 2023Don’t Stop Pretraining? Make Prompt-based Fine-tuning Powerful Learner
  31. NeurIPS 2023DPM-Solver-v3: Improved Diffusion ODE Solver with Empirical Model Statistics
  32. NeurIPS 2023Efficient Low-rank Backpropagation for Vision Transformer Adaptation
  33. NeurIPS 2023EHRSHOT: An EHR Benchmark for Few-Shot Evaluation of Foundation Models
  34. NeurIPS 2023Equivariant Adaptation of Large Pretrained Models
  35. NeurIPS 2023Exact recovery and Bregman hard clustering of node-attributed Stochastic Block Model
  36. NeurIPS 2023Fast Trainable Projection for Robust Fine-tuning
  37. NeurIPS 2023Feature Adaptation for Sparse Linear Regression
  38. NeurIPS 2023Fine-Grained Human Feedback Gives Better Rewards for Language Model Training
  39. NeurIPS 2023FineMoGen: Fine-Grained Spatio-Temporal Motion Generation and Editing
  40. NeurIPS 2023Foundation Model is Efficient Multimodal Multitask Model Selector
  41. NeurIPS 2023Generalized Logit Adjustment: Calibrating Fine-tuned Models by Removing Label Bias in Foundation Models
  42. NeurIPS 2023Generalized Semi-Supervised Learning via Self-Supervised Feature Adaptation
  43. NeurIPS 2023Geodesic Multi-Modal Mixup for Robust Fine-Tuning
  44. NeurIPS 2023Getting ViT in Shape: Scaling Laws for Compute-Optimal Model Design
  45. NeurIPS 2023GPT4Tools: Teaching Large Language Model to Use Tools via Self-instruction
  46. NeurIPS 2023HiBug: On Human-Interpretable Model Debug
  47. NeurIPS 2023Holistic Transfer: Towards Non-Disruptive Fine-Tuning with Partial Target Data
  48. NeurIPS 2023How to Fine-tune the Model: Unified Model Shift and Model Bias Policy Optimization
  49. NeurIPS 2023HyenaDNA: Long-Range Genomic Sequence Modeling at Single Nucleotide Resolution
  50. NeurIPS 2023Importance-aware Co-teaching for Offline Model-based Optimization

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