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 7 / 9 页

  1. ICLR 2025SaRA: High-Efficient Diffusion Model Fine-tuning with Progressive Sparse Low-Rank Adaptation
  2. ICLR 2025Scaling Diffusion Language Models via Adaptation from Autoregressive Models
  3. ICLR 2025Scaling Wearable Foundation Models
  4. ICLR 2025SD-LoRA: Scalable Decoupled Low-Rank Adaptation for Class Incremental Learning
  5. ICLR 2025SEAL: Safety-enhanced Aligned LLM Fine-tuning via Bilevel Data Selection
  6. ICLR 2025Second-Order Fine-Tuning without Pain for LLMs: A Hessian Informed Zeroth-Order Optimizer
  7. ICLR 2025Selective Aggregation for Low-Rank Adaptation in Federated Learning
  8. ICLR 2025Semantic Loss Guided Data Efficient Supervised Fine Tuning for Safe Responses in LLMs
  9. ICLR 2025Semi-Supervised CLIP Adaptation by Enforcing Semantic and Trapezoidal Consistency
  10. ICLR 2025Should VLMs be Pre-trained with Image Data?
  11. ICLR 2025SMT: Fine-Tuning Large Language Models with Sparse Matrices
  12. ICLR 2025Sparse autoencoders reveal selective remapping of visual concepts during adaptation
  13. ICLR 2025Specialized Foundation Models Struggle to Beat Supervised Baselines
  14. ICLR 2025Spectral-Refiner: Accurate Fine-Tuning of Spatiotemporal Fourier Neural Operator for Turbulent Flows
  15. ICLR 2025SRSA: Skill Retrieval and Adaptation for Robotic Assembly Tasks
  16. ICLR 2025STAFF: Speculative Coreset Selection for Task-Specific Fine-tuning
  17. ICLR 2025STBLLM: Breaking the 1-Bit Barrier with Structured Binary LLMs
  18. ICLR 2025Task-Adaptive Pretrained Language Models via Clustered-Importance Sampling
  19. ICLR 2025TC-MoE: Augmenting Mixture of Experts with Ternary Expert Choice
  20. ICLR 2025Teaching LLMs How to Learn with Contextual Fine-Tuning
  21. ICLR 2025Tell me about yourself: LLMs are aware of their learned behaviors
  22. ICLR 2025To Code or Not To Code? Exploring Impact of Code in Pre-training
  23. ICLR 2025Towards Fast, Specialized Machine Learning Force Fields: Distilling Foundation Models via Energy Hessians
  24. ICLR 2025Towards Foundation Models for Mixed Integer Linear Programming
  25. ICLR 2025Training-Free Activation Sparsity in Large Language Models
  26. ICLR 2025Transformer-Squared: Self-adaptive LLMs
  27. ICLR 2025Unleashing the Power of Task-Specific Directions in Parameter Efficient Fine-tuning
  28. ICLR 2025Unlocking Efficient, Scalable, and Continual Knowledge Editing with Basis-Level Representation Fine-Tuning
  29. ICLR 2025Unveiling the Secret Recipe: A Guide For Supervised Fine-Tuning Small LLMs
  30. ICLR 2025VILA-U: a Unified Foundation Model Integrating Visual Understanding and Generation
  31. ICLR 2025Weakly-Supervised Affordance Grounding Guided by Part-Level Semantic Priors
  32. ICLR 2025When Attention Sink Emerges in Language Models: An Empirical View
  33. ICLR 2025X-Fi: A Modality-Invariant Foundation Model for Multimodal Human Sensing
  34. ICLR 2025Zero-shot Imputation with Foundation Inference Models for Dynamical Systems
  35. ICLR 2025Zeroth-Order Fine-Tuning of LLMs with Transferable Static Sparsity
  36. ICLR 2025ZooProbe: A Data Engine for Evaluating, Exploring, and Evolving Large-scale Training Data for Multimodal LLMs
  37. ICLR 2024A Foundation Model for Error Correction Codes
  38. ICLR 2024A Hard-to-Beat Baseline for Training-free CLIP-based Adaptation
  39. ICLR 2024Adapting to Distribution Shift by Visual Domain Prompt Generation
  40. ICLR 2024Advancing the Lower Bounds: an Accelerated, Stochastic, Second-order Method with Optimal Adaptation to Inexactness
  41. ICLR 2024An Emulator for Fine-tuning Large Language Models using Small Language Models
  42. ICLR 2024AutoLoRa: An Automated Robust Fine-Tuning Framework
  43. ICLR 2024AutoVP: An Automated Visual Prompting Framework and Benchmark
  44. ICLR 2024Batched Low-Rank Adaptation of Foundation Models
  45. ICLR 2024Bayesian Low-rank Adaptation for Large Language Models
  46. ICLR 2024BrainLM: A foundation model for brain activity recordings
  47. ICLR 2024C-TPT: Calibrated Test-Time Prompt Tuning for Vision-Language Models via Text Feature Dispersion
  48. ICLR 2024CLAP: Collaborative Adaptation for Patchwork Learning
  49. ICLR 2024Convolution Meets LoRA: Parameter Efficient Finetuning for Segment Anything Model
  50. ICLR 2024DePT: Decomposed Prompt Tuning 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