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 14 / 30 页

  1. CVPR 2025SapiensID: Foundation for Human Recognition
  2. CVPR 2025SCAP: Transductive Test-Time Adaptation via Supportive Clique-based Attribute Prompting
  3. CVPR 2025Sensitivity-Aware Efficient Fine-Tuning via Compact Dynamic-Rank Adaptation
  4. CVPR 2025SketchFusion: Learning Universal Sketch Features through Fusing Foundation Models
  5. CVPR 2025SoMA: Singular Value Decomposed Minor Components Adaptation for Domain Generalizable Representation Learning
  6. CVPR 2025Tartan IMU: A Light Foundation Model for Inertial Positioning in Robotics
  7. CVPR 2025Task-Specific Gradient Adaptation for Few-Shot One-Class Classification
  8. CVPR 2025Thin-Shell-SfT: Fine-Grained Monocular Non-rigid 3D Surface Tracking with Neural Deformation Fields
  9. CVPR 2025Towards More General Video-based Deepfake Detection through Facial Component Guided Adaptation for Foundation Model
  10. CVPR 2025Universal Actions for Enhanced Embodied Foundation Models
  11. CVPR 2025Unsupervised Foundation Model-Agnostic Slide-Level Representation Learning
  12. CVPR 2025vesselFM: A Foundation Model for Universal 3D Blood Vessel Segmentation
  13. CVPR 2025Visual Persona: Foundation Model for Full-Body Human Customization
  14. CVPR 2025VladVA: Discriminative Fine-tuning of LVLMs
  15. ICLR 2025A Quantum Circuit-Based Compression Perspective for Parameter-Efficient Learning
  16. ICLR 2025AdaRankGrad: Adaptive Gradient Rank and Moments for Memory-Efficient LLMs Training and Fine-Tuning
  17. ICLR 2025Addax: Utilizing Zeroth-Order Gradients to Improve Memory Efficiency and Performance of SGD for Fine-Tuning Language Models
  18. ICLR 2025ADePT: Adaptive Decomposed Prompt Tuning for Parameter-Efficient Fine-tuning
  19. ICLR 2025Agent Skill Acquisition for Large Language Models via CycleQD
  20. ICLR 2025Amulet: ReAlignment During Test Time for Personalized Preference Adaptation of LLMs
  21. ICLR 2025An Auditing Test to Detect Behavioral Shift in Language Models
  22. ICLR 2025Analyzing and Boosting the Power of Fine-Grained Visual Recognition for Multi-modal Large Language Models
  23. ICLR 2025As Simple as Fine-tuning: LLM Alignment via Bidirectional Negative Feedback Loss
  24. ICLR 2025Better autoregressive regression with LLMs via regression-aware fine-tuning
  25. ICLR 2025Booster: Tackling Harmful Fine-tuning for Large Language Models via Attenuating Harmful Perturbation
  26. ICLR 2025CBraMod: A Criss-Cross Brain Foundation Model for EEG Decoding
  27. ICLR 2025ComLoRA: A Competitive Learning Approach for Enhancing LoRA
  28. ICLR 2025Computational Limits of Low-Rank Adaptation (LoRA) Fine-Tuning for Transformer Models
  29. ICLR 2025CONDA: Adaptive Concept Bottleneck for Foundation Models Under Distribution Shifts
  30. ICLR 2025CryoFM: A Flow-based Foundation Model for Cryo-EM Densities
  31. ICLR 2025CTSyn: A Foundation Model for Cross Tabular Data Generation
  32. ICLR 2025DaWin: Training-free Dynamic Weight Interpolation for Robust Adaptation
  33. ICLR 2025dEBORA: Efficient Bilevel Optimization-based low-Rank Adaptation
  34. ICLR 2025Decoupling Angles and Strength in Low-rank Adaptation
  35. ICLR 2025DELIFT: Data Efficient Language model Instruction Fine-Tuning
  36. ICLR 2025Directional Gradient Projection for Robust Fine-Tuning of Foundation Models
  37. ICLR 2025Do as I do (Safely): Mitigating Task-Specific Fine-tuning Risks in Large Language Models
  38. ICLR 2025Does Spatial Cognition Emerge in Frontier Models?
  39. ICLR 2025DRESSing Up LLM: Efficient Stylized Question-Answering via Style Subspace Editing
  40. ICLR 2025Dynamic Low-Rank Sparse Adaptation for Large Language Models
  41. ICLR 2025DynaPrompt: Dynamic Test-Time Prompt Tuning
  42. ICLR 2025Efficient Model Editing with Task-Localized Sparse Fine-tuning
  43. ICLR 2025Efficiently Learning at Test-Time: Active Fine-Tuning of LLMs
  44. ICLR 2025Emergence of meta-stable clustering in mean-field transformer models
  45. ICLR 2025Emerging Safety Attack and Defense in Federated Instruction Tuning of Large Language Models
  46. ICLR 2025Encryption-Friendly LLM Architecture
  47. ICLR 2025Enhancing Cognition and Explainability of Multimodal Foundation Models with Self-Synthesized Data
  48. ICLR 2025Enhancing Federated Domain Adaptation with Multi-Domain Prototype-Based Federated Fine-Tuning
  49. ICLR 2025Enhancing Zeroth-order Fine-tuning for Language Models with Low-rank Structures
  50. ICLR 2025Ensembles of Low-Rank Expert Adapters

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