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 18 / 30 页

  1. ICML 2025On Fine-Grained Distinct Element Estimation
  2. ICML 2025Parameter-Efficient Fine-Tuning of State Space Models
  3. ICML 2025Peri-LN: Revisiting Normalization Layer in the Transformer Architecture
  4. ICML 2025PertEval-scFM: Benchmarking Single-Cell Foundation Models for Perturbation Effect Prediction
  5. ICML 2025Portable Reward Tuning: Towards Reusable Fine-Tuning across Different Pretrained Models
  6. ICML 2025Projection Pursuit Density Ratio Estimation
  7. ICML 2025Promoting Ensemble Diversity with Interactive Bayesian Distributional Robustness for Fine-tuning Foundation Models
  8. ICML 2025Provable and Practical Online Learning Rate Adaptation with Hypergradient Descent
  9. ICML 2025Proxy-FDA: Proxy-based Feature Distribution Alignment for Fine-tuning Vision Foundation Models without Forgetting
  10. ICML 2025Raptor: Scalable Train-Free Embeddings for 3D Medical Volumes Leveraging Pretrained 2D Foundation Models
  11. ICML 2025RepLoRA: Reparameterizing Low-rank Adaptation via the Perspective of Mixture of Experts
  12. ICML 2025Restoring Calibration for Aligned Large Language Models: A Calibration-Aware Fine-Tuning Approach
  13. ICML 2025Rethinking the Bias of Foundation Model under Long-tailed Distribution
  14. ICML 2025SAM2Act: Integrating Visual Foundation Model with A Memory Architecture for Robotic Manipulation
  15. ICML 2025SAN: Hypothesizing Long-Term Synaptic Development and Neural Engram Mechanism in Scalable Model's Parameter-Efficient Fine-Tuning
  16. ICML 2025Scaling Laws for Forgetting during Finetuning with Pretraining Data Injection
  17. ICML 2025SeedLoRA: A Fusion Approach to Efficient LLM Fine-Tuning
  18. ICML 2025Sketch to Adapt: Fine-Tunable Sketches for Efficient LLM Adaptation
  19. ICML 2025SPACE: Your Genomic Profile Predictor is a Powerful DNA Foundation Model
  20. ICML 2025SparseLoRA: Accelerating LLM Fine-Tuning with Contextual Sparsity
  21. ICML 2025SToFM: a Multi-scale Foundation Model for Spatial Transcriptomics
  22. ICML 2025TabICL: A Tabular Foundation Model for In-Context Learning on Large Data
  23. ICML 2025TabPFN Unleashed: A Scalable and Effective Solution to Tabular Classification Problems
  24. ICML 2025Tackling Dimensional Collapse toward Comprehensive Universal Domain Adaptation
  25. ICML 2025Task-Agnostic Pre-training and Task-Guided Fine-tuning for Versatile Diffusion Planner
  26. ICML 2025Test-time Adaptation on Graphs via Adaptive Subgraph-based Selection and Regularized Prototypes
  27. ICML 2025Text-to-LoRA: Instant Transformer Adaption
  28. ICML 2025The Double-Ellipsoid Geometry of CLIP
  29. ICML 2025Theoretical Performance Guarantees for Partial Domain Adaptation via Partial Optimal Transport
  30. ICML 2025Token Cleaning: Fine-Grained Data Selection for LLM Supervised Fine-Tuning
  31. ICML 2025Towards Graph Foundation Models: Learning Generalities Across Graphs via Task-Trees
  32. ICML 2025Towards Understanding Fine-Tuning Mechanisms of LLMs via Circuit Analysis
  33. ICML 2025TreeLoRA: Efficient Continual Learning via Layer-Wise LoRAs Guided by a Hierarchical Gradient-Similarity Tree
  34. ICML 2025Understanding Overadaptation in Supervised Fine-Tuning: The Role of Ensemble Methods
  35. ICML 2025Upweighting Easy Samples in Fine-Tuning Mitigates Forgetting
  36. ICML 2025WeGeFT: Weight‑Generative Fine‑Tuning for Multi‑Faceted Efficient Adaptation of Large Models
  37. ICML 2025What Has a Foundation Model Found? Inductive Bias Reveals World Models
  38. ICML 2025When Can Proxies Improve the Sample Complexity of Preference Learning?
  39. ICML 2025Zero-Shot Adaptation of Parameter-Efficient Fine-Tuning in Diffusion Models
  40. NeurIPS 2025A Closer Look to Positive-Unlabeled Learning from Fine-grained Perspectives: An Empirical Study
  41. NeurIPS 2025Activated LoRA: Fine-tuned LLMs for Intrinsics
  42. NeurIPS 2025AdaLRS: Loss-Guided Adaptive Learning Rate Search for Efficient Foundation Model Pretraining
  43. NeurIPS 2025AdaMSS: Adaptive Multi-Subspace Approach for Parameter-Efficient Fine-Tuning
  44. NeurIPS 2025Adaptive LoRA Experts Allocation and Selection for Federated Fine-Tuning
  45. NeurIPS 2025Advancing Compositional Awareness in CLIP with Efficient Fine-Tuning
  46. NeurIPS 2025AI Progress Should Be Measured by Capability-Per-Resource, Not Scale Alone: A Framework for Gradient-Guided Resource Allocation in LLMs
  47. NeurIPS 2025AION-1: Omnimodal Foundation Model for Astronomical Sciences
  48. NeurIPS 2025All You Need is One: Capsule Prompt Tuning with a Single Vector
  49. NeurIPS 2025AltLoRA: Towards Better Gradient Approximation in Low-Rank Adaptation with Alternating Projections
  50. NeurIPS 2025An Investigation of Memorization Risk in Healthcare Foundation 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