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 404 篇，第 8 / 9 页

  1. ICLR 2024Differentially Private Synthetic Data via Foundation Model APIs 1: Images
  2. ICLR 2024Directly Fine-Tuning Diffusion Models on Differentiable Rewards
  3. ICLR 2024Dissecting Sample Hardness: A Fine-Grained Analysis of Hardness Characterization Methods for Data-Centric AI
  4. ICLR 2024Dynamic Sparse No Training: Training-Free Fine-tuning for Sparse LLMs
  5. ICLR 2024Enhancing Transferable Adversarial Attacks on Vision Transformers through Gradient Normalization Scaling and High-Frequency Adaptation
  6. ICLR 2024Entropy is not Enough for Test-Time Adaptation: From the Perspective of Disentangled Factors
  7. ICLR 2024Exploring the Common Appearance-Boundary Adaptation for Nighttime Optical Flow
  8. ICLR 2024Fast Imitation via Behavior Foundation Models
  9. ICLR 2024Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!
  10. ICLR 2024Fine-Tuning Enhances Existing Mechanisms: A Case Study on Entity Tracking
  11. ICLR 2024Fine-Tuning Language Models for Factuality
  12. ICLR 2024Get more for less: Principled Data Selection for Warming Up Fine-Tuning in LLMs
  13. ICLR 2024Gradual Domain Adaptation via Gradient Flow
  14. ICLR 2024Increasing Model Capacity for Free: A Simple Strategy for Parameter Efficient Fine-tuning
  15. ICLR 2024Mechanistically analyzing the effects of fine-tuning on procedurally defined tasks
  16. ICLR 2024Memory-Assisted Sub-Prototype Mining for Universal Domain Adaptation
  17. ICLR 2024Navigating Text-To-Image Customization: From LyCORIS Fine-Tuning to Model Evaluation
  18. ICLR 2024Neural Fine-Tuning Search for Few-Shot Learning
  19. ICLR 2024OVOR: OnePrompt with Virtual Outlier Regularization for Rehearsal-Free Class-Incremental Learning
  20. ICLR 2024Pre-Training and Fine-Tuning Generative Flow Networks
  21. ICLR 2024Principled Federated Domain Adaptation: Gradient Projection and Auto-Weighting
  22. ICLR 2024Project and Probe: Sample-Efficient Adaptation by Interpolating Orthogonal Features
  23. ICLR 2024QA-LoRA: Quantization-Aware Low-Rank Adaptation of Large Language Models
  24. ICLR 2024Selective Mixup Fine-Tuning for Optimizing Non-Decomposable Objectives
  25. ICLR 2024The False Promise of Imitating Proprietary Language Models
  26. ICLR 2024Towards Few-Shot Adaptation of Foundation Models via Multitask Finetuning
  27. ICLR 2024Towards Green AI in Fine-tuning Large Language Models via Adaptive Backpropagation
  28. ICLR 2024Towards Robust and Efficient Cloud-Edge Elastic Model Adaptation via Selective Entropy Distillation
  29. ICLR 2024Towards Seamless Adaptation of Pre-trained Models for Visual Place Recognition
  30. ICLR 2024Two-stage LLM Fine-tuning with Less Specialization and More Generalization
  31. ICLR 2024UniTabE: A Universal Pretraining Protocol for Tabular Foundation Model in Data Science
  32. ICLR 2024VeRA: Vector-based Random Matrix Adaptation
  33. ICLR 2024When Do Prompting and Prefix-Tuning Work? A Theory of Capabilities and Limitations
  34. ICLR 2024WizardCoder: Empowering Code Large Language Models with Evol-Instruct
  35. ICLR 2024WizardLM: Empowering Large Pre-Trained Language Models to Follow Complex Instructions
  36. ICLR 2024Zero-Shot Robustification of Zero-Shot Models
  37. ICLR 2023A Closer Look at Model Adaptation using Feature Distortion and Simplicity Bias
  38. ICLR 2023Consolidator: Mergable Adapter with Group Connections for Visual Adaptation
  39. ICLR 2023Dirichlet-based Uncertainty Calibration for Active Domain Adaptation
  40. ICLR 2023Divide to Adapt: Mitigating Confirmation Bias for Domain Adaptation of Black-Box Predictors
  41. ICLR 2023Energy-Based Test Sample Adaptation for Domain Generalization
  42. ICLR 2023ESD: Expected Squared Difference as a Tuning-Free Trainable Calibration Measure
  43. ICLR 2023Graph Domain Adaptation via Theory-Grounded Spectral Regularization
  44. ICLR 2023Hyper-Decision Transformer for Efficient Online Policy Adaptation
  45. ICLR 2023Interneurons accelerate learning dynamics in recurrent neural networks for statistical adaptation
  46. ICLR 2023Lossless Adaptation of Pretrained Vision Models For Robotic Manipulation
  47. ICLR 2023Preserving Pre-trained Features Helps Calibrate Fine-tuned Language Models
  48. ICLR 2023Self-Distillation for Further Pre-training of Transformers
  49. ICLR 2023Surgical Fine-Tuning Improves Adaptation to Distribution Shifts
  50. ICLR 2023The Trade-off between Universality and Label Efficiency of Representations from Contrastive Learning

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