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 531 篇，第 4 / 11 页

  1. NeurIPS 2026SPIRIT: Speed-Driven Online Adaptation for Self-Speculative Decoding
  2. NeurIPS 2026Stability Regimes for Framing-Sensitive Fine-Tuning in Language Models
  3. NeurIPS 2026Tabular Foundation Model for Generative Modelling
  4. NeurIPS 2026TACO: Towards Task-Consistent Open-Vocabulary Adaptation in Video Recognition
  5. NeurIPS 2026Tadpole: Autoencoders as Foundation Models for 3D PDEs with Online Learning
  6. NeurIPS 2026The Geometry of Alignment Collapse: When Fine-Tuning Breaks Safety
  7. NeurIPS 2026The Optimal Control Foundation of Early Exits – Turnpikes and ResNets
  8. NeurIPS 2026The Surprising Effectiveness of Deleting Weights in LLM Reasoning and Adaptation
  9. NeurIPS 2026Towards Identifying Dominant Low-Rank Subspaces in Zeroth-Order Fine-Tuning
  10. NeurIPS 2026Towards Reconstructing Geographically Diverse Architecture with 3D Foundation Models
  11. NeurIPS 2026Trainable Sparse Attention via Hybrid Top-k+Top-p Masking and Distillation Fine-Tuning
  12. NeurIPS 2026Trust the Direction, Search the Step: Zero-and-First-Order Methods for LLM Fine-Tuning
  13. NeurIPS 2026TS-ICL: A Flexible Time-Indexed Foundation Model for Time Series via In-Context Learning
  14. NeurIPS 2026Tune-Up Open-Weight CLIP: Optimization Framework for Self-Supervised Fine-tuning of CLIP
  15. NeurIPS 2026Tuning the Tuner
  16. NeurIPS 2026U-MOF: Uncertainty-Guided Parameter-Efficient Multi-Objective Fine-Tuning for Long-Tailed Recognition
  17. NeurIPS 2026Uncertainty-Aware Listwise Reinforcement Fine-Tuning for Fine-Grained Visual Classification
  18. NeurIPS 2026Unified Panoramic Geometry Estimation via Multi-View Foundation Models
  19. NeurIPS 2026Unveiling Implicit Advantage Symmetry: Why GRPO Struggles with Exploration and Difficulty Adaptation
  20. NeurIPS 2026Vibe-Spike: An Energy-Preserving EEG Foundation Model Through the Landscape of Neural Coherence
  21. NeurIPS 2026What DNA Foundation Models Learn Beyond Sequence Composition
  22. NeurIPS 2026What do EEG Foundation Models Capture from Human Brain Signals?
  23. NeurIPS 2026What Does an Observability Forecasting Foundation Model Know?
  24. NeurIPS 2026What Drives Test-Time Adaptation for CLIP? A Controlled Empirical Study from an Update Perspective
  25. NeurIPS 2026When Catastrophic Inheritance Meets Forgetting in Continual Adaptation of Foundation Models
  26. NeurIPS 2026When does LeJEPA learn a World Model?
  27. NeurIPS 2026When the Merge Coefficient Stops Mattering: Proximity Regularized Merging for Continual LoRA Adaptation
  28. NeurIPS 2026When to Trust a PFN: Detecting Harmful Shift in Tabular Foundation Models
  29. NeurIPS 2026Where Do We (Not) Need Temporal Context in Low-Resource Video Task Adaptation?
  30. NeurIPS 2026Where You Backpropagate Matters: Token Hypothesis for Memory-Efficient Fine-Tuning
  31. NeurIPS 2026Who Needs Labels? Adapting Vision Foundation Models With the Metadata You Already Have
  32. NeurIPS 2026You CAN Teach an Old Model New Tricks: Domain Adaptation via Complementary Subspace Expansion
  33. NeurIPS 2025A Closer Look to Positive-Unlabeled Learning from Fine-grained Perspectives: An Empirical Study
  34. NeurIPS 2025Activated LoRA: Fine-tuned LLMs for Intrinsics
  35. NeurIPS 2025AdaLRS: Loss-Guided Adaptive Learning Rate Search for Efficient Foundation Model Pretraining
  36. NeurIPS 2025AdaMSS: Adaptive Multi-Subspace Approach for Parameter-Efficient Fine-Tuning
  37. NeurIPS 2025Adaptive LoRA Experts Allocation and Selection for Federated Fine-Tuning
  38. NeurIPS 2025Advancing Compositional Awareness in CLIP with Efficient Fine-Tuning
  39. NeurIPS 2025AI Progress Should Be Measured by Capability-Per-Resource, Not Scale Alone: A Framework for Gradient-Guided Resource Allocation in LLMs
  40. NeurIPS 2025AION-1: Omnimodal Foundation Model for Astronomical Sciences
  41. NeurIPS 2025All You Need is One: Capsule Prompt Tuning with a Single Vector
  42. NeurIPS 2025AltLoRA: Towards Better Gradient Approximation in Low-Rank Adaptation with Alternating Projections
  43. NeurIPS 2025An Investigation of Memorization Risk in Healthcare Foundation Models
  44. NeurIPS 2025Attack via Overfitting: 10-shot Benign Fine-tuning to Jailbreak LLMs
  45. NeurIPS 2025AuroRA: Breaking Low-Rank Bottleneck of LoRA with Nonlinear Mapping
  46. NeurIPS 2025Axial Neural Networks for Dimension-Free Foundation Models
  47. NeurIPS 2025Beyond Higher Rank: Token-wise Input-Output Projections for Efficient Low-Rank Adaptation
  48. NeurIPS 2025Bigram Subnetworks: Mapping to Next Tokens in Transformer Language Models
  49. NeurIPS 2025BlockScan: Detecting Anomalies in Blockchain Transactions
  50. NeurIPS 2025Boosting Skeleton-based Zero-Shot Action Recognition with Training-Free Test-Time 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