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 28 / 30 页

  1. CVPR 2023Semi-Supervised Domain Adaptation With Source Label Adaptation
  2. CVPR 2023Test Time Adaptation With Regularized Loss for Weakly Supervised Salient Object Detection
  3. CVPR 2023Towards Better Stability and Adaptability: Improve Online Self-Training for Model Adaptation in Semantic Segmentation
  4. CVPR 2023Towards Fast Adaptation of Pretrained Contrastive Models for Multi-Channel Video-Language Retrieval
  5. CVPR 2023Train/Test-Time Adaptation With Retrieval
  6. CVPR 2023Trainable Projected Gradient Method for Robust Fine-Tuning
  7. CVPR 2023TWINS: A Fine-Tuning Framework for Improved Transferability of Adversarial Robustness and Generalization
  8. ICLR 2023A Closer Look at Model Adaptation using Feature Distortion and Simplicity Bias
  9. ICLR 2023Consolidator: Mergable Adapter with Group Connections for Visual Adaptation
  10. ICLR 2023Dirichlet-based Uncertainty Calibration for Active Domain Adaptation
  11. ICLR 2023Divide to Adapt: Mitigating Confirmation Bias for Domain Adaptation of Black-Box Predictors
  12. ICLR 2023Energy-Based Test Sample Adaptation for Domain Generalization
  13. ICLR 2023ESD: Expected Squared Difference as a Tuning-Free Trainable Calibration Measure
  14. ICLR 2023Graph Domain Adaptation via Theory-Grounded Spectral Regularization
  15. ICLR 2023Hyper-Decision Transformer for Efficient Online Policy Adaptation
  16. ICLR 2023Interneurons accelerate learning dynamics in recurrent neural networks for statistical adaptation
  17. ICLR 2023Lossless Adaptation of Pretrained Vision Models For Robotic Manipulation
  18. ICLR 2023Preserving Pre-trained Features Helps Calibrate Fine-tuned Language Models
  19. ICLR 2023Self-Distillation for Further Pre-training of Transformers
  20. ICLR 2023Surgical Fine-Tuning Improves Adaptation to Distribution Shifts
  21. ICLR 2023The Trade-off between Universality and Label Efficiency of Representations from Contrastive Learning
  22. ICLR 2023Token Merging: Your ViT But Faster
  23. ICLR 2023TVSPrune - Pruning Non-discriminative filters via Total Variation separability of intermediate representations without fine tuning
  24. ICLR 2023Using Language to Extend to Unseen Domains
  25. ICLR 2023When Source-Free Domain Adaptation Meets Learning with Noisy Labels
  26. ICML 2023A Kernel-Based View of Language Model Fine-Tuning
  27. ICML 2023AdaNPC: Exploring Non-Parametric Classifier for Test-Time Adaptation
  28. ICML 2023Are Neurons Actually Collapsed? On the Fine-Grained Structure in Neural Representations
  29. ICML 2023Bidirectional Adaptation for Robust Semi-Supervised Learning with Inconsistent Data Distributions
  30. ICML 2023ClimaX: A foundation model for weather and climate
  31. ICML 2023CocktailSGD: Fine-tuning Foundation Models over 500Mbps Networks
  32. ICML 2023Conditional Tree Matching for Inference-Time Adaptation of Tree Prediction Models
  33. ICML 2023Constant Matters: Fine-grained Error Bound on Differentially Private Continual Observation
  34. ICML 2023Cross-Modal Fine-Tuning: Align then Refine
  35. ICML 2023Curious Replay for Model-based Adaptation
  36. ICML 2023Double-Weighting for Covariate Shift Adaptation
  37. ICML 2023Efficient Personalized Federated Learning via Sparse Model-Adaptation
  38. ICML 2023Explore and Exploit the Diverse Knowledge in Model Zoo for Domain Generalization
  39. ICML 2023Exploring the Benefits of Training Expert Language Models over Instruction Tuning
  40. ICML 2023Flash: Concept Drift Adaptation in Federated Learning
  41. ICML 2023Flexible Model Aggregation for Quantile Regression
  42. ICML 2023How Many Perturbations Break This Model? Evaluating Robustness Beyond Adversarial Accuracy
  43. ICML 2023Human-Timescale Adaptation in an Open-Ended Task Space
  44. ICML 2023In Search for a Generalizable Method for Source Free Domain Adaptation
  45. ICML 2023LegendreTron: Uprising Proper Multiclass Loss Learning
  46. ICML 2023Magneto: A Foundation Transformer
  47. ICML 2023Master-ASR: Achieving Multilingual Scalability and Low-Resource Adaptation in ASR with Modular Learning
  48. ICML 2023MetaDiffuser: Diffusion Model as Conditional Planner for Offline Meta-RL
  49. ICML 2023Mitigating Spurious Correlations in Multi-modal Models during Fine-tuning
  50. ICML 2023Model Transferability with Responsive Decision Subjects

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