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 30 / 30 页

  1. NeurIPS 2023Inner-Outer Aware Reconstruction Model for Monocular 3D Scene Reconstruction
  2. NeurIPS 2023Interactive Multi-fidelity Learning for Cost-effective Adaptation of Language Model with Sparse Human Supervision
  3. NeurIPS 2023Make Pre-trained Model Reversible: From Parameter to Memory Efficient Fine-Tuning
  4. NeurIPS 2023Mixed Samples as Probes for Unsupervised Model Selection in Domain Adaptation
  5. NeurIPS 2023MixFormerV2: Efficient Fully Transformer Tracking
  6. NeurIPS 2023Mixture Weight Estimation and Model Prediction in Multi-source Multi-target Domain Adaptation
  7. NeurIPS 2023Model Shapley: Equitable Model Valuation with Black-box Access
  8. NeurIPS 2023Model Sparsity Can Simplify Machine Unlearning
  9. NeurIPS 2023Model-enhanced Vector Index
  10. NeurIPS 2023Moment Matching Denoising Gibbs Sampling
  11. NeurIPS 2023MoVie: Visual Model-Based Policy Adaptation for View Generalization
  12. NeurIPS 2023Near-Optimal $k$-Clustering in the Sliding Window Model
  13. NeurIPS 2023On Sparse Modern Hopfield Model
  14. NeurIPS 2023On the Connection between Pre-training Data Diversity and Fine-tuning Robustness
  15. NeurIPS 2023Optimal Transport Model Distributional Robustness
  16. NeurIPS 2023OV-PARTS: Towards Open-Vocabulary Part Segmentation
  17. NeurIPS 2023Parameter-efficient Tuning of Large-scale Multimodal Foundation Model
  18. NeurIPS 2023PIXIU: A Comprehensive Benchmark, Instruction Dataset and Large Language Model for Finance
  19. NeurIPS 2023Preference-grounded Token-level Guidance for Language Model Fine-tuning
  20. NeurIPS 2023R-divergence for Estimating Model-oriented Distribution Discrepancy
  21. NeurIPS 2023RDumb: A simple approach that questions our progress in continual test-time adaptation
  22. NeurIPS 2023Res-Tuning: A Flexible and Efficient Tuning Paradigm via Unbinding Tuner from Backbone
  23. NeurIPS 2023Retaining Beneficial Information from Detrimental Data for Neural Network Repair
  24. NeurIPS 2023Rewarded soups: towards Pareto-optimal alignment by interpolating weights fine-tuned on diverse rewards
  25. NeurIPS 2023SegRefiner: Towards Model-Agnostic Segmentation Refinement with Discrete Diffusion Process
  26. NeurIPS 2023Self-Chained Image-Language Model for Video Localization and Question Answering
  27. NeurIPS 2023SPA: A Graph Spectral Alignment Perspective for Domain Adaptation
  28. NeurIPS 2023Subspace Identification for Multi-Source Domain Adaptation
  29. NeurIPS 2023Synthetic-to-Real Pose Estimation with Geometric Reconstruction
  30. NeurIPS 2023Task-Robust Pre-Training for Worst-Case Downstream Adaptation
  31. NeurIPS 2023The Goldilocks of Pragmatic Understanding: Fine-Tuning Strategy Matters for Implicature Resolution by LLMs
  32. NeurIPS 2023TIES-Merging: Resolving Interference When Merging Models
  33. NeurIPS 2023To Repeat or Not To Repeat: Insights from Scaling LLM under Token-Crisis
  34. NeurIPS 2023Topological RANSAC for instance verification and retrieval without fine-tuning
  35. NeurIPS 2023Towards Foundation Models for Scientific Machine Learning: Characterizing Scaling and Transfer Behavior
  36. NeurIPS 2023Towards Optimal Caching and Model Selection for Large Model Inference
  37. NeurIPS 2023Towards Stable Backdoor Purification through Feature Shift Tuning
  38. NeurIPS 2023Training-free Diffusion Model Adaptation for Variable-Sized Text-to-Image Synthesis
  39. NeurIPS 2023Undirected Probabilistic Model for Tensor Decomposition
  40. NeurIPS 2023WalkLM: A Uniform Language Model Fine-tuning Framework for Attributed Graph Embedding
  41. NeurIPS 2023When Visual Prompt Tuning Meets Source-Free Domain Adaptive Semantic Segmentation
  42. NeurIPS 2023Winner-Take-All Column Row Sampling for Memory Efficient Adaptation of Language Model

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