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 94 篇，第 2 / 2 页

  1. NeurIPS 2024MetaLA: Unified Optimal Linear Approximation to Softmax Attention Map
  2. NeurIPS 2024Model Fusion through Bayesian Optimization in Language Model Fine-Tuning
  3. NeurIPS 2024Multi-modal Transfer Learning between Biological Foundation Models
  4. NeurIPS 2024Order-Independence Without Fine Tuning
  5. NeurIPS 2024PACE: Marrying generalization in PArameter-efficient fine-tuning with Consistency rEgularization
  6. NeurIPS 2024Personalized Adapter for Large Meteorology Model on Devices: Towards Weather Foundation Models
  7. NeurIPS 2024PiSSA: Principal Singular Values and Singular Vectors Adaptation of Large Language Models
  8. NeurIPS 2024Poseidon: Efficient Foundation Models for PDEs
  9. NeurIPS 2024Pre-training Differentially Private Models with Limited Public Data
  10. NeurIPS 2024Predicting the Performance of Foundation Models via Agreement-on-the-Line
  11. NeurIPS 2024PrivAuditor: Benchmarking Data Protection Vulnerabilities in LLM Adaptation Techniques
  12. NeurIPS 2024Probabilistic Federated Prompt-Tuning with Non-IID and Imbalanced Data
  13. NeurIPS 2024Prompt Tuning Strikes Back: Customizing Foundation Models with Low-Rank Prompt Adaptation
  14. NeurIPS 2024QuanTA: Efficient High-Rank Fine-Tuning of LLMs with Quantum-Informed Tensor Adaptation
  15. NeurIPS 2024RAMP: Boosting Adversarial Robustness Against Multiple $l_p$ Perturbations for Universal Robustness
  16. NeurIPS 2024Rethinking Weight Decay for Robust Fine-Tuning of Foundation Models
  17. NeurIPS 2024Retrieval & Fine-Tuning for In-Context Tabular Models
  18. NeurIPS 2024Risk-Averse Fine-tuning of Large Language Models
  19. NeurIPS 2024S$^{2}$FT: Efficient, Scalable and Generalizable LLM Fine-tuning by Structured Sparsity
  20. NeurIPS 2024Segment Any Change
  21. NeurIPS 2024Self-Taught Recognizer: Toward Unsupervised Adaptation for Speech Foundation Models
  22. NeurIPS 2024Shaping the distribution of neural responses with interneurons in a recurrent circuit model
  23. NeurIPS 2024SHED: Shapley-Based Automated Dataset Refinement for Instruction Fine-Tuning
  24. NeurIPS 2024SmallToLarge (S2L): Scalable Data Selection for Fine-tuning Large Language Models by Summarizing Training Trajectories of Small Models
  25. NeurIPS 2024Source Code Foundation Models are Transferable Binary Analysis Knowledge Bases
  26. NeurIPS 2024Spectral Adapter: Fine-Tuning in Spectral Space
  27. NeurIPS 2024Stepping Forward on the Last Mile
  28. NeurIPS 2024Stress-Testing Capability Elicitation With Password-Locked Models
  29. NeurIPS 2024Style Adaptation and Uncertainty Estimation for Multi-Source Blended-Target Domain Adaptation
  30. NeurIPS 2024SVFT: Parameter-Efficient Fine-Tuning with Singular Vectors
  31. NeurIPS 2024Synthesize, Partition, then Adapt: Eliciting Diverse Samples from Foundation Models
  32. NeurIPS 2024Text-space Graph Foundation Models: Comprehensive Benchmarks and New Insights
  33. NeurIPS 2024The Impact of Initialization on LoRA Finetuning Dynamics
  34. NeurIPS 2024The Representation Landscape of Few-Shot Learning and Fine-Tuning in Large Language Models
  35. NeurIPS 2024Towards Calibrated Robust Fine-Tuning of Vision-Language Models
  36. NeurIPS 2024Uncertainty-aware Fine-tuning of Segmentation Foundation Models
  37. NeurIPS 2024Understanding Linear Probing then Fine-tuning Language Models from NTK Perspective
  38. NeurIPS 2024UniDSeg: Unified Cross-Domain 3D Semantic Segmentation via Visual Foundation Models Prior
  39. NeurIPS 2024Unveiling LoRA Intrinsic Ranks via Salience Analysis
  40. NeurIPS 2024Vaccine: Perturbation-aware Alignment for Large Language Models against Harmful Fine-tuning Attack
  41. NeurIPS 2024VB-LoRA: Extreme Parameter Efficient Fine-Tuning with Vector Banks
  42. NeurIPS 2024Vision Foundation Model Enables Generalizable Object Pose Estimation
  43. NeurIPS 2024What does guidance do? A fine-grained analysis in a simple setting
  44. NeurIPS 2024WONDERBREAD: A Benchmark for Evaluating Multimodal Foundation Models on Business Process Management Tasks

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