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 8 / 30 页

  1. ICML 2026Learning in the Fisher Subspace: A Guided Initialization for LoRA Fine-Tuning
  2. ICML 2026LimiX-2M: Mitigating Low-Rank Collapse and Attention Bottlenecks in Tabular Foundation Models
  3. ICML 2026Low Kruskal-Rank Adaptation
  4. ICML 2026LOZO+: Provably Efficient Zeroth-Order Fine-Tuning via Greedy Low-Rank Subspace Selection
  5. ICML 2026Mantis: Lightweight Foundation Model for Time Series Classification
  6. ICML 2026MDGMIX: Boundary-Aware Subgraph Mixing for Multi-Domain Graph Pre-Training
  7. ICML 2026Message Tuning Outshines Graph Prompt Tuning: A Prismatic Space Perspective
  8. ICML 2026MetaPerch: Learning from metadata for bioacoustics foundation models
  9. ICML 2026Midtraining Bridges Pretraining and Posttraining Distributions
  10. ICML 2026MODEL SOUPS NEED ONLY ONE INGREDIENT
  11. ICML 2026Multi-Label Test-Time Adaptation with Bayesian Conditional Priors
  12. ICML 2026MultiLoReFT: Decoupling Shared and Modality-Specific Subspaces in Multimodal Learning via Low-Rank Representation Fine-Tuning
  13. ICML 2026NeuroCLUS: A Foundation Model with Functional Clustering for Intracranial Neural Decoding
  14. ICML 2026No Need to Train Your RDB Foundation Model
  15. ICML 2026Olivia: Harmonizing Time Series Foundation Models with Power Spectral Density
  16. ICML 2026Omni-fMRI: A Universal Atlas-Free fMRI Foundation Model
  17. ICML 2026On the Entropy Dynamics in Reinforcement Fine-Tuning of Large Language Models
  18. ICML 2026Origo: Interpretable Multi-physics PDE Foundation Model through Neural Operator Splitting
  19. ICML 2026PATCHCODE: Discrete Latent Predictive Learning for EEG Foundation Model
  20. ICML 2026PFT: Phonon Fine-tuning for Machine Learned Interatomic Potentials
  21. ICML 2026PISA: Privacy-Preserving Split Adaptation with Model IP Protection
  22. ICML 2026PixCLIP: Towards Fine-grained Vision-Language Understanding via Any-granularity Pixel-Text Alignment
  23. ICML 2026PLATE: Plasticity-Tunable Efficient Adapters for Geometry-Aware Continual Learning
  24. ICML 2026PLoRA: Efficient Concurrent LoRA Training for Large Language Models
  25. ICML 2026Preference Goal Tuning: Post-Training as Latent Control for Frozen Policies
  26. ICML 2026Progressive Graph Structure Adjustment for Homophily Shift Adaptation
  27. ICML 2026Quantifying the Uncertainty of Foundation Models with Singular Value Ensembles
  28. ICML 2026Residual-Guided Multi-Resolution Refinement of Foundation Models: A Case Study in Drought Forecasting
  29. ICML 2026Rethinking the Flow-based Gradual Domain Adaptation: A Semi-Dual Optimal Transport Perspective
  30. ICML 2026SALAAD: Sparse And Low-Rank Adaptation via ADMM for Large Language Model Inference
  31. ICML 2026Saving Foundation Flow-Matching Priors for Inverse Problems
  32. ICML 2026Scaling Behavior in Model Fine-tuning for Audio DeepFake Detection
  33. ICML 2026ScaLoRA: Optimally Scaled Low-Rank Adaptation for Efficient High-Rank Fine-Tuning
  34. ICML 2026scDEBART: Predicting in silico Single-Cell Perturbation Responses via Large-Scale Differential Expression Learning
  35. ICML 2026See More, Forecast Better and Faster: Enhancing Time Series Foundation Models via Inference-Time Plug-and-Play Downsampling
  36. ICML 2026SHERPA: Fine-tuning Segment Anything Models with Task-relevant Guidance
  37. ICML 2026SHINE: A Scalable In-Context Hypernetwork for Mapping Context to LoRA in a Single Pass
  38. ICML 2026SleepMaMi: A Universal Sleep Foundation Model for Integrating Macro- and Micro-structures
  39. ICML 2026SliceFine: The Universal Winning-Slice Hypothesis for Pretrained Networks
  40. ICML 2026SpanNorm: Reconciling Training Stability and Performance in Deep Transformers
  41. ICML 2026SPARD: Defending Harmful Fine-Tuning Attack via Safety Projection with Relevance–Diversity Data Selection
  42. ICML 2026Spectral Imbalance Causes Forgetting in Low-Rank Continual Adaptation
  43. ICML 2026SPR: A Structured Prompt Refinement Network for Modality Missing
  44. ICML 2026StarEmbed: Benchmarking Time Series Foundation Models on Astronomical Observations of Variable Stars
  45. ICML 2026Subgroup Discovery with the Cox Model
  46. ICML 2026SURGE: Surrogate Gradient Adaptation in Binary Neural Networks
  47. ICML 2026Surgery: Mitigating Harmful Fine-Tuning for Large Language Models via Attention Sink
  48. ICML 2026TabICLv2: A Better, Faster, Scalable, and Open Tabular Foundation Model
  49. ICML 2026TabMGP: Martingale Posterior with TabPFN
  50. ICML 2026TabSwift: An Efficient Tabular Foundation Model with Row-Wise Attention

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