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 404 篇，第 5 / 9 页

  1. ICLR 2025Computational Limits of Low-Rank Adaptation (LoRA) Fine-Tuning for Transformer Models
  2. ICLR 2025CONDA: Adaptive Concept Bottleneck for Foundation Models Under Distribution Shifts
  3. ICLR 2025CryoFM: A Flow-based Foundation Model for Cryo-EM Densities
  4. ICLR 2025CTSyn: A Foundation Model for Cross Tabular Data Generation
  5. ICLR 2025DaWin: Training-free Dynamic Weight Interpolation for Robust Adaptation
  6. ICLR 2025dEBORA: Efficient Bilevel Optimization-based low-Rank Adaptation
  7. ICLR 2025Decoupling Angles and Strength in Low-rank Adaptation
  8. ICLR 2025DELIFT: Data Efficient Language model Instruction Fine-Tuning
  9. ICLR 2025Directional Gradient Projection for Robust Fine-Tuning of Foundation Models
  10. ICLR 2025Do as I do (Safely): Mitigating Task-Specific Fine-tuning Risks in Large Language Models
  11. ICLR 2025Does Spatial Cognition Emerge in Frontier Models?
  12. ICLR 2025DRESSing Up LLM: Efficient Stylized Question-Answering via Style Subspace Editing
  13. ICLR 2025Dynamic Low-Rank Sparse Adaptation for Large Language Models
  14. ICLR 2025DynaPrompt: Dynamic Test-Time Prompt Tuning
  15. ICLR 2025Efficient Model Editing with Task-Localized Sparse Fine-tuning
  16. ICLR 2025Efficiently Learning at Test-Time: Active Fine-Tuning of LLMs
  17. ICLR 2025Emergence of meta-stable clustering in mean-field transformer models
  18. ICLR 2025Emerging Safety Attack and Defense in Federated Instruction Tuning of Large Language Models
  19. ICLR 2025Encryption-Friendly LLM Architecture
  20. ICLR 2025Enhancing Cognition and Explainability of Multimodal Foundation Models with Self-Synthesized Data
  21. ICLR 2025Enhancing Federated Domain Adaptation with Multi-Domain Prototype-Based Federated Fine-Tuning
  22. ICLR 2025Enhancing Zeroth-order Fine-tuning for Language Models with Low-rank Structures
  23. ICLR 2025Ensembles of Low-Rank Expert Adapters
  24. ICLR 2025Exploring the Effectiveness of Object-Centric Representations in Visual Question Answering: Comparative Insights with Foundation Models
  25. ICLR 2025Federated Residual Low-Rank Adaptation of Large Language Models
  26. ICLR 2025Fine-Tuning Attention Modules Only: Enhancing Weight Disentanglement in Task Arithmetic
  27. ICLR 2025Fine-tuning can Help Detect Pretraining Data from Large Language Models
  28. ICLR 2025Fine-tuning with Reserved Majority for Noise Reduction
  29. ICLR 2025Forget the Data and Fine-Tuning! Just Fold the Network to Compress
  30. ICLR 2025Fundamental Limitations on Subquadratic Alternatives to Transformers
  31. ICLR 2025Fundamental Limits of Prompt Tuning Transformers: Universality, Capacity and Efficiency
  32. ICLR 2025Generative Adapter: Contextualizing Language Models in Parameters with A Single Forward Pass
  33. ICLR 2025Generative Representational Instruction Tuning
  34. ICLR 2025GeoLoRA: Geometric integration for parameter efficient fine-tuning
  35. ICLR 2025GOAL: A Generalist Combinatorial Optimization Agent Learner
  36. ICLR 2025HiRA: Parameter-Efficient Hadamard High-Rank Adaptation for Large Language Models
  37. ICLR 2025Hyper-Connections
  38. ICLR 2025Inference-Aware Fine-Tuning for Best-of-N Sampling in Large Language Models
  39. ICLR 2025Instruct-SkillMix: A Powerful Pipeline for LLM Instruction Tuning
  40. ICLR 2025Intelligent Go-Explore: Standing on the Shoulders of Giant Foundation Models
  41. ICLR 2025Intervening Anchor Token: Decoding Strategy in Alleviating Hallucinations for MLLMs
  42. ICLR 2025Jamba: Hybrid Transformer-Mamba Language Models
  43. ICLR 2025KaSA: Knowledge-Aware Singular-Value Adaptation of Large Language Models
  44. ICLR 2025Knowledge Graph Finetuning Enhances Knowledge Manipulation in Large Language Models
  45. ICLR 2025Kolmogorov-Arnold Transformer
  46. ICLR 2025Large Convolutional Model Tuning via Filter Subspace
  47. ICLR 2025Learning Diverse Attacks on Large Language Models for Robust Red-Teaming and Safety Tuning
  48. ICLR 2025Learning to Adapt Frozen CLIP for Few-Shot Test-Time Domain Adaptation
  49. ICLR 2025LiFT: Learning to Fine-Tune via Bayesian Parameter Efficient Meta Fine-Tuning
  50. ICLR 2025LoCA: Location-Aware Cosine Adaptation for Parameter-Efficient Fine-Tuning

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