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 6 / 9 页

  1. ICLR 2025LoLCATs: On Low-Rank Linearizing of Large Language Models
  2. ICLR 2025LoR-VP: Low-Rank Visual Prompting for Efficient Vision Model Adaptation
  3. ICLR 2025LoRA-Pro: Are Low-Rank Adapters Properly Optimized?
  4. ICLR 2025LoRA-X: Bridging Foundation Models with Training-Free Cross-Model Adaptation
  5. ICLR 2025LoRA3D: Low-Rank Self-Calibration of 3D Geometric Foundation models
  6. ICLR 2025Lotus: Diffusion-based Visual Foundation Model for High-quality Dense Prediction
  7. ICLR 2025Maintaining Structural Integrity in Parameter Spaces for Parameter Efficient Fine-tuning
  8. ICLR 2025MallowsPO: Fine-Tune Your LLM with Preference Dispersions
  9. ICLR 2025MambaPEFT: Exploring Parameter-Efficient Fine-Tuning for Mamba
  10. ICLR 2025MambaQuant: Quantizing the Mamba Family with Variance Aligned Rotation Methods
  11. ICLR 2025Matryoshka Multimodal Models
  12. ICLR 2025Merging LoRAs like Playing LEGO: Pushing the Modularity of LoRA to Extremes Through Rank-Wise Clustering
  13. ICLR 2025MeteoRA: Multiple-tasks Embedded LoRA for Large Language Models
  14. ICLR 2025Mitigating Memorization in Language Models
  15. ICLR 2025Mix-CPT: A Domain Adaptation Framework via Decoupling Knowledge Learning and Format Alignment
  16. ICLR 2025Mix-LN: Unleashing the Power of Deeper Layers by Combining Pre-LN and Post-LN
  17. ICLR 2025MM1.5: Methods, Analysis & Insights from Multimodal LLM Fine-tuning
  18. ICLR 2025Model Equality Testing: Which Model is this API Serving?
  19. ICLR 2025MoLEx: Mixture of Layer Experts for Fine-tuning with Sparse Upcycling
  20. ICLR 2025Montessori-Instruct: Generate Influential Training Data Tailored for Student Learning
  21. ICLR 2025MoS: Unleashing Parameter Efficiency of Low-Rank Adaptation with Mixture of Shards
  22. ICLR 2025MTSAM: Multi-Task Fine-Tuning for Segment Anything Model
  23. ICLR 2025Multiview Equivariance Improves 3D Correspondence Understanding with Minimal Feature Finetuning
  24. ICLR 2025Neural ODE Transformers: Analyzing Internal Dynamics and Adaptive Fine-tuning
  25. ICLR 2025Neural Phylogeny: Fine-Tuning Relationship Detection among Neural Networks
  26. ICLR 2025nGPT: Normalized Transformer with Representation Learning on the Hypersphere
  27. ICLR 2025NNsight and NDIF: Democratizing Access to Open-Weight Foundation Model Internals
  28. ICLR 2025NUDGE: Lightweight Non-Parametric Fine-Tuning of Embeddings for Retrieval
  29. ICLR 2025On the Optimization Landscape of Low Rank Adaptation Methods for Large Language Models
  30. ICLR 2025PaCA: Partial Connection Adaptation for Efficient Fine-Tuning
  31. ICLR 2025PEARL: Towards Permutation-Resilient LLMs
  32. ICLR 2025PortLLM: Personalizing Evolving Large Language Models with Training-Free and Portable Model Patches
  33. ICLR 2025Preserving Diversity in Supervised Fine-Tuning of Large Language Models
  34. ICLR 2025ProteinBench: A Holistic Evaluation of Protein Foundation Models
  35. ICLR 2025Q-SFT: Q-Learning for Language Models via Supervised Fine-Tuning
  36. ICLR 2025QERA: an Analytical Framework for Quantization Error Reconstruction
  37. ICLR 2025Quantized Spike-driven Transformer
  38. ICLR 2025Quantum-PEFT: Ultra parameter-efficient fine-tuning
  39. ICLR 2025RaSA: Rank-Sharing Low-Rank Adaptation
  40. ICLR 2025RDT-1B: a Diffusion Foundation Model for Bimanual Manipulation
  41. ICLR 2025Re-Imagining Multimodal Instruction Tuning: A Representation View
  42. ICLR 2025RECAST: Reparameterized, Compact weight Adaptation for Sequential Tasks
  43. ICLR 2025Recite, Reconstruct, Recollect: Memorization in LMs as a Multifaceted Phenomenon
  44. ICLR 2025Reconstructive Visual Instruction Tuning
  45. ICLR 2025Release the Powers of Prompt Tuning: Cross-Modality Prompt Transfer
  46. ICLR 2025Revisiting Convolution Architecture in the Realm of DNA Foundation Models
  47. ICLR 2025Revisiting Prefix-tuning: Statistical Benefits of Reparameterization among Prompts
  48. ICLR 2025ROUTE: Robust Multitask Tuning and Collaboration for Text-to-SQL
  49. ICLR 2025RRM: Robust Reward Model Training Mitigates Reward Hacking
  50. ICLR 2025SaLoRA: Safety-Alignment Preserved Low-Rank Adaptation

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