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 20 / 30 页

  1. NeurIPS 2025Fourier Analysis Network
  2. NeurIPS 2025From Pretraining to Pathology: How Noise Leads to Catastrophic Inheritance in Medical Models
  3. NeurIPS 2025Gains: Fine-grained Federated Domain Adaptation in Open Set
  4. NeurIPS 2025GaRA-SAM: Robustifying Segment Anything Model with Gated-Rank Adaptation
  5. NeurIPS 2025Gated Integration of Low-Rank Adaptation for Continual Learning of Large Language Models
  6. NeurIPS 2025Generating Informative Samples for Risk-Averse Fine-Tuning of Downstream Tasks
  7. NeurIPS 2025GeoAda: Efficiently Finetune Geometric Diffusion Models with Equivariant Adapters
  8. NeurIPS 2025GeoLink: Empowering Remote Sensing Foundation Model with OpenStreetMap Data
  9. NeurIPS 2025Geometry-Aware Collaborative Multi-Solutions Optimizer for Model Fine-Tuning with Parameter Efficiency
  10. NeurIPS 2025GFM-RAG: Graph Foundation Model for Retrieval Augmented Generation
  11. NeurIPS 2025GoRA: Gradient-driven Adaptive Low Rank Adaptation
  12. NeurIPS 2025GraLoRA: Granular Low-Rank Adaptation for Parameter-Efficient Fine-Tuning
  13. NeurIPS 2025GRAVER: Generative Graph Vocabularies for Robust Graph Foundation Models Fine-tuning
  14. NeurIPS 2025Harmony in Divergence: Towards Fast, Accurate, and Memory-efficient Zeroth-order LLM Fine-tuning
  15. NeurIPS 2025Hyperbolic Fine-Tuning for Large Language Models
  16. NeurIPS 2025Implicit Modeling for Transferability Estimation of Vision Foundation Models
  17. NeurIPS 2025Improving Data Efficiency for LLM Reinforcement Fine-tuning Through Difficulty-targeted Online Data Selection and Rollout Replay
  18. NeurIPS 2025In-Context Learning of Stochastic Differential Equations with Foundation Inference Models
  19. NeurIPS 2025Investigating Hallucinations of Time Series Foundation Models through Signal Subspace Analysis
  20. NeurIPS 2025Iterative Foundation Model Fine-Tuning on Multiple Rewards
  21. NeurIPS 2025JanusDNA: A Powerful Bi-directional Hybrid DNA Foundation Model
  22. NeurIPS 2025Language Models Can Predict Their Own Behavior
  23. NeurIPS 2025Latent Space Factorization in LoRA
  24. NeurIPS 2025LaX: Boosting Low-Rank Training of Foundation Models via Latent Crossing
  25. NeurIPS 2025Learning Source-Free Domain Adaptation for Visible-Infrared Person Re-Identification
  26. NeurIPS 2025Learning to Factorize Spatio-Temporal Foundation Models
  27. NeurIPS 2025Learning to Think: Information-Theoretic Reinforcement Fine-Tuning for LLMs
  28. NeurIPS 2025Less is More: Unlocking Specialization of Time Series Foundation Models via Structured Pruning
  29. NeurIPS 2025Linearization Explains Fine-Tuning in Large Language Models
  30. NeurIPS 2025Loquetier: A Virtualized Multi-LoRA Framework for Unified LLM Fine-tuning and Serving
  31. NeurIPS 2025LoRA vs Full Fine-tuning: An Illusion of Equivalence
  32. NeurIPS 2025LoRASuite: Efficient LoRA Adaptation Across Large Language Model Upgrades
  33. NeurIPS 2025LoTA-QAF: Lossless Ternary Adaptation for Quantization-Aware Fine-Tuning
  34. NeurIPS 2025LT-Soups: Bridging Head and Tail Classes via Subsampled Model Soups
  35. NeurIPS 2025LUNA: Efficient and Topology-Agnostic Foundation Model for EEG Signal Analysis
  36. NeurIPS 2025Magical: Medical Lay Language Generation via Semantic Invariance and Layperson-tailored Adaptation
  37. NeurIPS 2025MedMax: Mixed-Modal Instruction Tuning for Training Biomedical Assistants
  38. NeurIPS 2025Metis: A Foundation Speech Generation Model with Masked Generative Pre-training
  39. NeurIPS 2025MimeQA: Towards Socially-Intelligent Nonverbal Foundation Models
  40. NeurIPS 2025MindGYM: What Matters in Question Synthesis for Thinking-Centric Fine-Tuning?
  41. NeurIPS 2025Minimax-Optimal Univariate Function Selection in Sparse Additive Models: Rates, Adaptation, and the Estimation-Selection Gap
  42. NeurIPS 2025Mitigating Forgetting in LLM Fine-Tuning via Low-Perplexity Token Learning
  43. NeurIPS 2025Mitra: Mixed Synthetic Priors for Enhancing Tabular Foundation Models
  44. NeurIPS 2025MokA: Multimodal Low-Rank Adaptation for MLLMs
  45. NeurIPS 2025Multi-Scale Finetuning for Encoder-based Time Series Foundation Models
  46. NeurIPS 2025Multimodal 3D Genome Pre-training
  47. NeurIPS 2025Neural Networks for Learnable and Scalable Influence Estimation of Instruction Fine-Tuning Data
  48. NeurIPS 2025NeurIPT: Foundation Model for Neural Interfaces
  49. NeurIPS 2025NormFit: A Lightweight Solution for Few-Shot Federated Learning with Non-IID Data
  50. NeurIPS 2025OmniDraft: A cross-vocabulary, online adaptive drafter for on-device speculative decoding

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