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 17 / 30 页

  1. ICLR 2025Towards Foundation Models for Mixed Integer Linear Programming
  2. ICLR 2025Training-Free Activation Sparsity in Large Language Models
  3. ICLR 2025Transformer-Squared: Self-adaptive LLMs
  4. ICLR 2025Unleashing the Power of Task-Specific Directions in Parameter Efficient Fine-tuning
  5. ICLR 2025Unlocking Efficient, Scalable, and Continual Knowledge Editing with Basis-Level Representation Fine-Tuning
  6. ICLR 2025Unveiling the Secret Recipe: A Guide For Supervised Fine-Tuning Small LLMs
  7. ICLR 2025VILA-U: a Unified Foundation Model Integrating Visual Understanding and Generation
  8. ICLR 2025Weakly-Supervised Affordance Grounding Guided by Part-Level Semantic Priors
  9. ICLR 2025When Attention Sink Emerges in Language Models: An Empirical View
  10. ICLR 2025X-Fi: A Modality-Invariant Foundation Model for Multimodal Human Sensing
  11. ICLR 2025Zero-shot Imputation with Foundation Inference Models for Dynamical Systems
  12. ICLR 2025Zeroth-Order Fine-Tuning of LLMs with Transferable Static Sparsity
  13. ICLR 2025ZooProbe: A Data Engine for Evaluating, Exploring, and Evolving Large-scale Training Data for Multimodal LLMs
  14. ICML 2025A Bayesian Model Selection Criterion for Selecting Pretraining Checkpoints
  15. ICML 2025A Stronger Mixture of Low-Rank Experts for Fine-Tuning Foundation Models
  16. ICML 2025Adapting to Evolving Adversaries with Regularized Continual Robust Training
  17. ICML 2025AdaPTS: Adapting Univariate Foundation Models to Probabilistic Multivariate Time Series Forecasting
  18. ICML 2025Are Large Brainwave Foundation Models Capable Yet ? Insights from Fine-Tuning
  19. ICML 2025Benign Samples Matter! Fine-tuning On Outlier Benign Samples Severely Breaks Safety
  20. ICML 2025Beyond Sensor Data: Foundation Models of Behavioral Data from Wearables Improve Health Predictions
  21. ICML 2025Beyond Zero Initialization: Investigating the Impact of Non-Zero Initialization on LoRA Fine-Tuning Dynamics
  22. ICML 2025Boosting Multi-Domain Fine-Tuning of Large Language Models through Evolving Interactions between Samples
  23. ICML 2025Canonical Rank Adaptation: An Efficient Fine-Tuning Strategy for Vision Transformers
  24. ICML 2025Come Together, But Not Right Now: A Progressive Strategy to Boost Low-Rank Adaptation
  25. ICML 2025Contextures: Representations from Contexts
  26. ICML 2025Does Low Rank Adaptation Lead to Lower Robustness against Training-Time Attacks?
  27. ICML 2025Efficient Personalized Adaptation for Physiological Signal Foundation Model
  28. ICML 2025ELoRA: Low-Rank Adaptation for Equivariant GNNs
  29. ICML 2025Enhancing Foundation Models for Time Series Forecasting via Wavelet-based Tokenization
  30. ICML 2025Enhancing Foundation Models with Federated Domain Knowledge Infusion
  31. ICML 2025ExPLoRA: Parameter-Efficient Extended Pre-Training to Adapt Vision Transformers under Domain Shifts
  32. ICML 2025Fast and Low-Cost Genomic Foundation Models via Outlier Removal
  33. ICML 2025Flat-LoRA: Low-Rank Adaptation over a Flat Loss Landscape
  34. ICML 2025Foundation Model Insights and a Multi-Model Approach for Superior Fine-Grained One-shot Subset Selection
  35. ICML 2025From Weight-Based to State-Based Fine-Tuning: Further Memory Reduction on LoRA with Parallel Control
  36. ICML 2025GAPrompt: Geometry-Aware Point Cloud Prompt for 3D Vision Model
  37. ICML 2025Griffin: Towards a Graph-Centric Relational Database Foundation Model
  38. ICML 2025In-Context Adaptation to Concept Drift for Learned Database Operations
  39. ICML 2025In-Context Fine-Tuning for Time-Series Foundation Models
  40. ICML 2025InfoSAM: Fine-Tuning the Segment Anything Model from An Information-Theoretic Perspective
  41. ICML 2025Invariance Makes LLM Unlearning Resilient Even to Unanticipated Downstream Fine-Tuning
  42. ICML 2025L3A: Label-Augmented Analytic Adaptation for Multi-Label Class Incremental Learning
  43. ICML 2025Large Continual Instruction Assistant
  44. ICML 2025Learn from Downstream and Be Yourself in Multimodal Large Language Models Fine-Tuning
  45. ICML 2025Lightweight Online Adaption for Time Series Foundation Model Forecasts
  46. ICML 2025LoRA Training Provably Converges to a Low-Rank Global Minimum Or It Fails Loudly (But it Probably Won't Fail)
  47. ICML 2025MixMin: Finding Data Mixtures via Convex Minimization
  48. ICML 2025Moirai-MoE: Empowering Time Series Foundation Models with Sparse Mixture of Experts
  49. ICML 2025NextCoder: Robust Adaptation of Code LMs to Diverse Code Edits
  50. ICML 2025OmniArch: Building Foundation Model for Scientific Computing

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