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 22 / 30 页

  1. NeurIPS 2025UFT: Unifying Supervised and Reinforcement Fine-Tuning
  2. NeurIPS 2025UGM2N: An Unsupervised and Generalizable Mesh Movement Network via M-Uniform Loss
  3. NeurIPS 2025Understanding Prompt Tuning and In-Context Learning via Meta-Learning
  4. NeurIPS 2025Uni-LoRA: One Vector is All You Need
  5. NeurIPS 2025Unified Multimodal Chain-of-Thought Reward Model through Reinforcement Fine-Tuning
  6. NeurIPS 2025Unified Transferability Metrics for Time Series Foundation Models
  7. NeurIPS 2025UniTraj: Learning a Universal Trajectory Foundation Model from Billion-Scale Worldwide Traces
  8. NeurIPS 2025Unleashing Foundation Vision Models: Adaptive Transfer for Diverse Data-Limited Scientific Domains
  9. NeurIPS 2025VESSA: Video-based objEct-centric Self-Supervised Adaptation for Visual Foundation Models
  10. NeurIPS 2025VIPAMIN: Visual Prompt Initialization via Embedding Selection and Subspace Expansion
  11. NeurIPS 2025Walking the Tightrope: Autonomous Disentangling Beneficial and Detrimental Drifts in Non-Stationary Custom-Tuning
  12. NeurIPS 2025What Matters in Data for DPO?
  13. NeurIPS 2025Whose Instructions Count? Resolving Preference Bias in Instruction Fine-Tuning
  14. CVPR 20243D-LFM: Lifting Foundation Model
  15. CVPR 2024A Pedestrian is Worth One Prompt: Towards Language Guidance Person Re-Identification
  16. CVPR 2024Adaptive Random Feature Regularization on Fine-tuning Deep Neural Networks
  17. CVPR 2024All in One Framework for Multimodal Re-identification in the Wild
  18. CVPR 2024AM-RADIO: Agglomerative Vision Foundation Model Reduce All Domains Into One
  19. CVPR 2024ASAM: Boosting Segment Anything Model with Adversarial Tuning
  20. CVPR 2024Asymmetric Masked Distillation for Pre-Training Small Foundation Models
  21. CVPR 2024BioCLIP: A Vision Foundation Model for the Tree of Life
  22. CVPR 2024Boosting Image Quality Assessment through Efficient Transformer Adaptation with Local Feature Enhancement
  23. CVPR 2024Boosting Order-Preserving and Transferability for Neural Architecture Search: a Joint Architecture Refined Search and Fine-tuning Approach
  24. CVPR 2024Bootstrapping SparseFormers from Vision Foundation Models
  25. CVPR 2024Bridging Remote Sensors with Multisensor Geospatial Foundation Models
  26. CVPR 2024Collaborating Foundation Models for Domain Generalized Semantic Segmentation
  27. CVPR 2024DePT: Decoupled Prompt Tuning
  28. CVPR 2024Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data
  29. CVPR 2024Efficient Stitchable Task Adaptation
  30. CVPR 2024Feature Re-Embedding: Towards Foundation Model-Level Performance in Computational Pathology
  31. CVPR 2024Federated Online Adaptation for Deep Stereo
  32. CVPR 2024FedSelect: Personalized Federated Learning with Customized Selection of Parameters for Fine-Tuning
  33. CVPR 2024Few-Shot Object Detection with Foundation Models
  34. CVPR 2024From-Ground-To-Objects: Coarse-to-Fine Self-supervised Monocular Depth Estimation of Dynamic Objects with Ground Contact Prior
  35. CVPR 2024General Object Foundation Model for Images and Videos at Scale
  36. CVPR 2024Gradient-based Parameter Selection for Efficient Fine-Tuning
  37. CVPR 2024Improved Self-Training for Test-Time Adaptation
  38. CVPR 2024Improving the Generalization of Segmentation Foundation Model under Distribution Shift via Weakly Supervised Adaptation
  39. CVPR 2024InfLoRA: Interference-Free Low-Rank Adaptation for Continual Learning
  40. CVPR 2024LEAD: Learning Decomposition for Source-free Universal Domain Adaptation
  41. CVPR 2024Learning CNN on ViT: A Hybrid Model to Explicitly Class-specific Boundaries for Domain Adaptation
  42. CVPR 2024Low-Rank Rescaled Vision Transformer Fine-Tuning: A Residual Design Approach
  43. CVPR 2024Low-Resource Vision Challenges for Foundation Models
  44. CVPR 2024MoML: Online Meta Adaptation for 3D Human Motion Prediction
  45. CVPR 2024OmniGlue: Generalizable Feature Matching with Foundation Model Guidance
  46. CVPR 2024One-Shot Open Affordance Learning with Foundation Models
  47. CVPR 2024OneTracker: Unifying Visual Object Tracking with Foundation Models and Efficient Tuning
  48. CVPR 2024Open-Vocabulary 3D Semantic Segmentation with Foundation Models
  49. CVPR 2024OpenEQA: Embodied Question Answering in the Era of Foundation Models
  50. CVPR 2024Orthogonal Adaptation for Modular Customization of Diffusion Models

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