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 24 / 30 页

  1. ICLR 2024Neural Fine-Tuning Search for Few-Shot Learning
  2. ICLR 2024OVOR: OnePrompt with Virtual Outlier Regularization for Rehearsal-Free Class-Incremental Learning
  3. ICLR 2024Pre-Training and Fine-Tuning Generative Flow Networks
  4. ICLR 2024Principled Federated Domain Adaptation: Gradient Projection and Auto-Weighting
  5. ICLR 2024Project and Probe: Sample-Efficient Adaptation by Interpolating Orthogonal Features
  6. ICLR 2024QA-LoRA: Quantization-Aware Low-Rank Adaptation of Large Language Models
  7. ICLR 2024Selective Mixup Fine-Tuning for Optimizing Non-Decomposable Objectives
  8. ICLR 2024The False Promise of Imitating Proprietary Language Models
  9. ICLR 2024Towards Few-Shot Adaptation of Foundation Models via Multitask Finetuning
  10. ICLR 2024Towards Green AI in Fine-tuning Large Language Models via Adaptive Backpropagation
  11. ICLR 2024Towards Robust and Efficient Cloud-Edge Elastic Model Adaptation via Selective Entropy Distillation
  12. ICLR 2024Towards Seamless Adaptation of Pre-trained Models for Visual Place Recognition
  13. ICLR 2024Two-stage LLM Fine-tuning with Less Specialization and More Generalization
  14. ICLR 2024UniTabE: A Universal Pretraining Protocol for Tabular Foundation Model in Data Science
  15. ICLR 2024VeRA: Vector-based Random Matrix Adaptation
  16. ICLR 2024When Do Prompting and Prefix-Tuning Work? A Theory of Capabilities and Limitations
  17. ICLR 2024WizardCoder: Empowering Code Large Language Models with Evol-Instruct
  18. ICLR 2024WizardLM: Empowering Large Pre-Trained Language Models to Follow Complex Instructions
  19. ICLR 2024Zero-Shot Robustification of Zero-Shot Models
  20. ICML 2024A Closer Look at the Limitations of Instruction Tuning
  21. ICML 2024A decoder-only foundation model for time-series forecasting
  22. ICML 2024A Provably Effective Method for Pruning Experts in Fine-tuned Sparse Mixture-of-Experts
  23. ICML 2024Accelerating Transformer Pre-training with 2:4 Sparsity
  24. ICML 2024Active Label Correction for Semantic Segmentation with Foundation Models
  25. ICML 2024Asymmetry in Low-Rank Adapters of Foundation Models
  26. ICML 2024Batch Singular Value Polarization and Weighted Semantic Augmentation for Universal Domain Adaptation
  27. ICML 2024Bayesian Adaptation of Network Depth and Width for Continual Learning
  28. ICML 2024Bayesian Power Steering: An Effective Approach for Domain Adaptation of Diffusion Models
  29. ICML 2024By Tying Embeddings You Are Assuming the Distributional Hypothesis
  30. ICML 2024Compressible Dynamics in Deep Overparameterized Low-Rank Learning & Adaptation
  31. ICML 2024Connect Later: Improving Fine-tuning for Robustness with Targeted Augmentations
  32. ICML 2024Connecting the Dots: Collaborative Fine-tuning for Black-Box Vision-Language Models
  33. ICML 2024Covert Malicious Finetuning: Challenges in Safeguarding LLM Adaptation
  34. ICML 2024Data-Efficient Learning via Clustering-Based Sensitivity Sampling: Foundation Models and Beyond
  35. ICML 2024Debiased Offline Representation Learning for Fast Online Adaptation in Non-stationary Dynamics
  36. ICML 2024DeepPolar: Inventing Nonlinear Large-Kernel Polar Codes via Deep Learning
  37. ICML 2024Differentially Private Bias-Term Fine-tuning of Foundation Models
  38. ICML 2024Differentially Private Domain Adaptation with Theoretical Guarantees
  39. ICML 2024DoRA: Weight-Decomposed Low-Rank Adaptation
  40. ICML 2024DPZero: Private Fine-Tuning of Language Models without Backpropagation
  41. ICML 2024Erasing the Bias: Fine-Tuning Foundation Models for Semi-Supervised Learning
  42. ICML 2024ETHER: Efficient Finetuning of Large-Scale Models with Hyperplane Reflections
  43. ICML 2024Fine-grained Local Sensitivity Analysis of Standard Dot-Product Self-Attention
  44. ICML 2024Fine-tuning Reinforcement Learning Models is Secretly a Forgetting Mitigation Problem
  45. ICML 2024FlashST: A Simple and Universal Prompt-Tuning Framework for Traffic Prediction
  46. ICML 2024Foundation Policies with Hilbert Representations
  47. ICML 2024From Yes-Men to Truth-Tellers: Addressing Sycophancy in Large Language Models with Pinpoint Tuning
  48. ICML 2024Getting the most out of your tokenizer for pre-training and domain adaptation
  49. ICML 2024Gradual Divergence for Seamless Adaptation: A Novel Domain Incremental Learning Method
  50. ICML 2024Helpful or Harmful Data? Fine-tuning-free Shapley Attribution for Explaining Language Model Predictions

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