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 16 / 30 页

  1. ICLR 2025Neural ODE Transformers: Analyzing Internal Dynamics and Adaptive Fine-tuning
  2. ICLR 2025Neural Phylogeny: Fine-Tuning Relationship Detection among Neural Networks
  3. ICLR 2025nGPT: Normalized Transformer with Representation Learning on the Hypersphere
  4. ICLR 2025NNsight and NDIF: Democratizing Access to Open-Weight Foundation Model Internals
  5. ICLR 2025NUDGE: Lightweight Non-Parametric Fine-Tuning of Embeddings for Retrieval
  6. ICLR 2025On the Optimization Landscape of Low Rank Adaptation Methods for Large Language Models
  7. ICLR 2025PaCA: Partial Connection Adaptation for Efficient Fine-Tuning
  8. ICLR 2025PEARL: Towards Permutation-Resilient LLMs
  9. ICLR 2025PortLLM: Personalizing Evolving Large Language Models with Training-Free and Portable Model Patches
  10. ICLR 2025Preserving Diversity in Supervised Fine-Tuning of Large Language Models
  11. ICLR 2025ProteinBench: A Holistic Evaluation of Protein Foundation Models
  12. ICLR 2025Q-SFT: Q-Learning for Language Models via Supervised Fine-Tuning
  13. ICLR 2025QERA: an Analytical Framework for Quantization Error Reconstruction
  14. ICLR 2025Quantized Spike-driven Transformer
  15. ICLR 2025Quantum-PEFT: Ultra parameter-efficient fine-tuning
  16. ICLR 2025RaSA: Rank-Sharing Low-Rank Adaptation
  17. ICLR 2025RDT-1B: a Diffusion Foundation Model for Bimanual Manipulation
  18. ICLR 2025Re-Imagining Multimodal Instruction Tuning: A Representation View
  19. ICLR 2025RECAST: Reparameterized, Compact weight Adaptation for Sequential Tasks
  20. ICLR 2025Recite, Reconstruct, Recollect: Memorization in LMs as a Multifaceted Phenomenon
  21. ICLR 2025Reconstructive Visual Instruction Tuning
  22. ICLR 2025Release the Powers of Prompt Tuning: Cross-Modality Prompt Transfer
  23. ICLR 2025Revisiting Convolution Architecture in the Realm of DNA Foundation Models
  24. ICLR 2025Revisiting Prefix-tuning: Statistical Benefits of Reparameterization among Prompts
  25. ICLR 2025ROUTE: Robust Multitask Tuning and Collaboration for Text-to-SQL
  26. ICLR 2025RRM: Robust Reward Model Training Mitigates Reward Hacking
  27. ICLR 2025SaLoRA: Safety-Alignment Preserved Low-Rank Adaptation
  28. ICLR 2025SaRA: High-Efficient Diffusion Model Fine-tuning with Progressive Sparse Low-Rank Adaptation
  29. ICLR 2025Scaling Diffusion Language Models via Adaptation from Autoregressive Models
  30. ICLR 2025Scaling Wearable Foundation Models
  31. ICLR 2025SD-LoRA: Scalable Decoupled Low-Rank Adaptation for Class Incremental Learning
  32. ICLR 2025SEAL: Safety-enhanced Aligned LLM Fine-tuning via Bilevel Data Selection
  33. ICLR 2025Second-Order Fine-Tuning without Pain for LLMs: A Hessian Informed Zeroth-Order Optimizer
  34. ICLR 2025Selective Aggregation for Low-Rank Adaptation in Federated Learning
  35. ICLR 2025Semantic Loss Guided Data Efficient Supervised Fine Tuning for Safe Responses in LLMs
  36. ICLR 2025Semi-Supervised CLIP Adaptation by Enforcing Semantic and Trapezoidal Consistency
  37. ICLR 2025Should VLMs be Pre-trained with Image Data?
  38. ICLR 2025SMT: Fine-Tuning Large Language Models with Sparse Matrices
  39. ICLR 2025Sparse autoencoders reveal selective remapping of visual concepts during adaptation
  40. ICLR 2025Specialized Foundation Models Struggle to Beat Supervised Baselines
  41. ICLR 2025Spectral-Refiner: Accurate Fine-Tuning of Spatiotemporal Fourier Neural Operator for Turbulent Flows
  42. ICLR 2025SRSA: Skill Retrieval and Adaptation for Robotic Assembly Tasks
  43. ICLR 2025STAFF: Speculative Coreset Selection for Task-Specific Fine-tuning
  44. ICLR 2025STBLLM: Breaking the 1-Bit Barrier with Structured Binary LLMs
  45. ICLR 2025Task-Adaptive Pretrained Language Models via Clustered-Importance Sampling
  46. ICLR 2025TC-MoE: Augmenting Mixture of Experts with Ternary Expert Choice
  47. ICLR 2025Teaching LLMs How to Learn with Contextual Fine-Tuning
  48. ICLR 2025Tell me about yourself: LLMs are aware of their learned behaviors
  49. ICLR 2025To Code or Not To Code? Exploring Impact of Code in Pre-training
  50. ICLR 2025Towards Fast, Specialized Machine Learning Force Fields: Distilling Foundation Models via Energy Hessians

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