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 4 / 6 页

  1. ICML 2024Position: Graph Foundation Models Are Already Here
  2. ICML 2024Position: On the Societal Impact of Open Foundation Models
  3. ICML 2024Position: Why Tabular Foundation Models Should Be a Research Priority
  4. ICML 2024Preference Fine-Tuning of LLMs Should Leverage Suboptimal, On-Policy Data
  5. ICML 2024Prior Mismatch and Adaptation in PnP-ADMM with a Nonconvex Convergence Analysis
  6. ICML 2024Prompting a Pretrained Transformer Can Be a Universal Approximator
  7. ICML 2024Prompting is a Double-Edged Sword: Improving Worst-Group Robustness of Foundation Models
  8. ICML 2024Random Masking Finds Winning Tickets for Parameter Efficient Fine-tuning
  9. ICML 2024Recovering the Pre-Fine-Tuning Weights of Generative Models
  10. ICML 2024Reducing Fine-Tuning Memory Overhead by Approximate and Memory-Sharing Backpropagation
  11. ICML 2024Revisiting the Power of Prompt for Visual Tuning
  12. ICML 2024Riemannian Preconditioned LoRA for Fine-Tuning Foundation Models
  13. ICML 2024Robust CLIP: Unsupervised Adversarial Fine-Tuning of Vision Embeddings for Robust Large Vision-Language Models
  14. ICML 2024RoSA: Accurate Parameter-Efficient Fine-Tuning via Robust Adaptation
  15. ICML 2024Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models
  16. ICML 2024SAM-E: Leveraging Visual Foundation Model with Sequence Imitation for Embodied Manipulation
  17. ICML 2024Selecting Large Language Model to Fine-tune via Rectified Scaling Law
  18. ICML 2024Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models
  19. ICML 2024Sparse is Enough in Fine-tuning Pre-trained Large Language Models
  20. ICML 2024SPP: Sparsity-Preserved Parameter-Efficient Fine-Tuning for Large Language Models
  21. ICML 2024SuDA: Support-based Domain Adaptation for Sim2Real Hinge Joint Tracking with Flexible Sensors
  22. ICML 2024To Cool or not to Cool? Temperature Network Meets Large Foundation Models via DRO
  23. ICML 2024Towards Causal Foundation Model: on Duality between Optimal Balancing and Attention
  24. ICML 2024Transferring Knowledge From Large Foundation Models to Small Downstream Models
  25. ICML 2024Unleashing the Power of Meta-tuning for Few-shot Generalization Through Sparse Interpolated Experts
  26. ICML 2024Variance-reduced Zeroth-Order Methods for Fine-Tuning Language Models
  27. NeurIPS 2024A Hitchhiker's Guide to Fine-Grained Face Forgery Detection Using Common Sense Reasoning
  28. NeurIPS 2024A Simple yet Universal Framework for Depth Completion
  29. NeurIPS 2024B'MOJO: Hybrid State Space Realizations of Foundation Models with Eidetic and Fading Memory
  30. NeurIPS 2024BackdoorAlign: Mitigating Fine-tuning based Jailbreak Attack with Backdoor Enhanced Safety Alignment
  31. NeurIPS 2024Be Confident in What You Know: Bayesian Parameter Efficient Fine-Tuning of Vision Foundation Models
  32. NeurIPS 2024BLoB: Bayesian Low-Rank Adaptation by Backpropagation for Large Language Models
  33. NeurIPS 2024Brain-JEPA: Brain Dynamics Foundation Model with Gradient Positioning and Spatiotemporal Masking
  34. NeurIPS 2024Cell ontology guided transcriptome foundation model
  35. NeurIPS 2024Conformal Alignment: Knowing When to Trust Foundation Models with Guarantees
  36. NeurIPS 2024CorDA: Context-Oriented Decomposition Adaptation of Large Language Models for Task-Aware Parameter-Efficient Fine-tuning
  37. NeurIPS 2024Curriculum Fine-tuning of Vision Foundation Model for Medical Image Classification Under Label Noise
  38. NeurIPS 2024Diffusion Tuning: Transferring Diffusion Models via Chain of Forgetting
  39. NeurIPS 2024DistillNeRF: Perceiving 3D Scenes from Single-Glance Images by Distilling Neural Fields and Foundation Model Features
  40. NeurIPS 2024Do Multimodal Foundation Models Understand Enterprise Workflows? A Benchmark for Business Process Management Tasks
  41. NeurIPS 2024DropBP: Accelerating Fine-Tuning of Large Language Models by Dropping Backward Propagation
  42. NeurIPS 2024Dual Risk Minimization: Towards Next-Level Robustness in Fine-tuning Zero-Shot Models
  43. NeurIPS 2024Dual-Personalizing Adapter for Federated Foundation Models
  44. NeurIPS 2024Dynamic Tuning Towards Parameter and Inference Efficiency for ViT Adaptation
  45. NeurIPS 2024Efficient Adaptation of Pre-trained Vision Transformer via Householder Transformation
  46. NeurIPS 2024EMGBench: Benchmarking Out-of-Distribution Generalization and Adaptation for Electromyography
  47. NeurIPS 2024Empowering Visible-Infrared Person Re-Identification with Large Foundation Models
  48. NeurIPS 2024EMVP: Embracing Visual Foundation Model for Visual Place Recognition with Centroid-Free Probing
  49. NeurIPS 2024FairMedFM: Fairness Benchmarking for Medical Imaging Foundation Models
  50. NeurIPS 2024Federated Fine-tuning of Large Language Models under Heterogeneous Tasks and Client Resources

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