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 270 篇，第 5 / 6 页

  1. NeurIPS 2024Fight Back Against Jailbreaking via Prompt Adversarial Tuning
  2. NeurIPS 2024Fine-Tuning is Fine, if Calibrated
  3. NeurIPS 2024Fine-Tuning Personalization in Federated Learning to Mitigate Adversarial Clients
  4. NeurIPS 2024Flaws can be Applause: Unleashing Potential of Segmenting Ambiguous Objects in SAM
  5. NeurIPS 2024FLoRA: Federated Fine-Tuning Large Language Models with Heterogeneous Low-Rank Adaptations
  6. NeurIPS 2024FM-Delta: Lossless Compression for Storing Massive Fine-tuned Foundation Models
  7. NeurIPS 2024Free Lunch in Pathology Foundation Model: Task-specific Model Adaptation with Concept-Guided Feature Enhancement
  8. NeurIPS 2024Frozen-DETR: Enhancing DETR with Image Understanding from Frozen Foundation Models
  9. NeurIPS 2024GFT: Graph Foundation Model with Transferable Tree Vocabulary
  10. NeurIPS 2024HEMM: Holistic Evaluation of Multimodal Foundation Models
  11. NeurIPS 2024Historical Test-time Prompt Tuning for Vision Foundation Models
  12. NeurIPS 2024HydraLoRA: An Asymmetric LoRA Architecture for Efficient Fine-Tuning
  13. NeurIPS 2024Incremental Learning of Retrievable Skills For Efficient Continual Task Adaptation
  14. NeurIPS 2024Instruction Tuning Large Language Models to Understand Electronic Health Records
  15. NeurIPS 2024Interfacing Foundation Models' Embeddings
  16. NeurIPS 2024Is One GPU Enough? Pushing Image Generation at Higher-Resolutions with Foundation Models.
  17. NeurIPS 2024Keeping LLMs Aligned After Fine-tuning: The Crucial Role of Prompt Templates
  18. NeurIPS 2024KG-FIT: Knowledge Graph Fine-Tuning Upon Open-World Knowledge
  19. NeurIPS 2024Learning from Offline Foundation Features with Tensor Augmentations
  20. NeurIPS 2024LISA: Layerwise Importance Sampling for Memory-Efficient Large Language Model Fine-Tuning
  21. NeurIPS 2024Lisa: Lazy Safety Alignment for Large Language Models against Harmful Fine-tuning Attack
  22. NeurIPS 2024LoFiT: Localized Fine-tuning on LLM Representations
  23. NeurIPS 2024Long-Tailed Out-of-Distribution Detection via Normalized Outlier Distribution Adaptation
  24. NeurIPS 2024LoQT: Low-Rank Adapters for Quantized Pretraining
  25. NeurIPS 2024LoRA-GA: Low-Rank Adaptation with Gradient Approximation
  26. NeurIPS 2024MeshXL: Neural Coordinate Field for Generative 3D Foundation Models
  27. NeurIPS 2024MetaLA: Unified Optimal Linear Approximation to Softmax Attention Map
  28. NeurIPS 2024Model Fusion through Bayesian Optimization in Language Model Fine-Tuning
  29. NeurIPS 2024Multi-modal Transfer Learning between Biological Foundation Models
  30. NeurIPS 2024Order-Independence Without Fine Tuning
  31. NeurIPS 2024PACE: Marrying generalization in PArameter-efficient fine-tuning with Consistency rEgularization
  32. NeurIPS 2024Personalized Adapter for Large Meteorology Model on Devices: Towards Weather Foundation Models
  33. NeurIPS 2024PiSSA: Principal Singular Values and Singular Vectors Adaptation of Large Language Models
  34. NeurIPS 2024Poseidon: Efficient Foundation Models for PDEs
  35. NeurIPS 2024Pre-training Differentially Private Models with Limited Public Data
  36. NeurIPS 2024Predicting the Performance of Foundation Models via Agreement-on-the-Line
  37. NeurIPS 2024PrivAuditor: Benchmarking Data Protection Vulnerabilities in LLM Adaptation Techniques
  38. NeurIPS 2024Probabilistic Federated Prompt-Tuning with Non-IID and Imbalanced Data
  39. NeurIPS 2024Prompt Tuning Strikes Back: Customizing Foundation Models with Low-Rank Prompt Adaptation
  40. NeurIPS 2024QuanTA: Efficient High-Rank Fine-Tuning of LLMs with Quantum-Informed Tensor Adaptation
  41. NeurIPS 2024RAMP: Boosting Adversarial Robustness Against Multiple $l_p$ Perturbations for Universal Robustness
  42. NeurIPS 2024Rethinking Weight Decay for Robust Fine-Tuning of Foundation Models
  43. NeurIPS 2024Retrieval & Fine-Tuning for In-Context Tabular Models
  44. NeurIPS 2024Risk-Averse Fine-tuning of Large Language Models
  45. NeurIPS 2024S$^{2}$FT: Efficient, Scalable and Generalizable LLM Fine-tuning by Structured Sparsity
  46. NeurIPS 2024Segment Any Change
  47. NeurIPS 2024Self-Taught Recognizer: Toward Unsupervised Adaptation for Speech Foundation Models
  48. NeurIPS 2024Shaping the distribution of neural responses with interneurons in a recurrent circuit model
  49. NeurIPS 2024SHED: Shapley-Based Automated Dataset Refinement for Instruction Fine-Tuning
  50. NeurIPS 2024SmallToLarge (S2L): Scalable Data Selection for Fine-tuning Large Language Models by Summarizing Training Trajectories of Small 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