深度学习 · transfer learning论文趋势 2023–2026

主要结论

• 深度学习 · transfer learning论文从 2023 年的 56 篇降到 2026 年的 54 篇，热度在回落。
• NeurIPS 是发深度学习 · transfer learning论文最多的会议，2023–2026 年共 71 篇，占四个会议总量的 36%。
• 交叉方向里涨得最快的是多模态大模型：同时属于两个主题的论文从 2023 年的 2 篇增至 2026 年的 5 篇。
• 在「深度学习」的 11 个主题里，它的 2026 年论文数排第 11；同组增长最快的扩散模型是 4.1 倍，深度学习 · transfer learning是 1.0 倍。

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

• NeurIPS 2026Emergent Misalignment as Data-Mediated Transfer
• ICML 2026Transfer Learning in High-dimensional Ising Models
• ICLR 2026TiTok: Transfer Token-level Knowledge via Contrastive Excess to Transplant LoRA
• CVPR 2026Unlocking Positive Transfer in Incrementally Learning Surgical Instruments A Self-reflection
• NeurIPS 2025Asymmetric Duos: Sidekicks Improve Uncertainty
• ICML 2025An Improved Clique-Picking Algorithm for Counting Markov Equivalent DAGs via Super Cliques Transfer
• ICLR 2025GraphBridge: Towards Arbitrary Transfer Learning in GNNs
• CVPR 2025A4A: Adapter for Adapter Transfer via All-for-All Mapping for Cross-Architecture Models
• NeurIPS 2024Transfer Learning with Informative Priors: Simple Baselines Better than Previously Reported
• ICML 2024Adversarially Robust Hypothesis Transfer Learning
• ICLR 2024Geometrically Aligned Transfer Encoder for Inductive Transfer in Regression Tasks
• CVPR 2024Geometry Transfer for Stylizing Radiance Fields
• NeurIPS 2023Diffused Redundancy in Pre-trained Representations
• ICML 2023Hypothesis Transfer Learning with Surrogate Classification Losses: Generalization Bounds through Algorithmic Stability
• ICLR 2023Transfer Learning with Deep Tabular Models
• CVPR 2023A Data-Based Perspective on Transfer Learning
• NeurIPS 2026Learning Rate Transfer for Hybrid Transformer-SSM Architectures
• ICML 2026Transfer Learning in Nonparametric Regression with Deep ReLU Networks
• ICLR 2026Detect, Decide, Unlearn: A Transfer-Aware Framework for Continual Learning
• CVPR 2026Nonlinear Color Transfer via Learnable Bezier Flows

全部深度学习 · transfer learning论文

共 23 篇，第 1 / 1 页

1. NeurIPS 2023Combining Behaviors with the Successor Features Keyboard
2. NeurIPS 2023Conditional Adapters: Parameter-efficient Transfer Learning with Fast Inference
3. NeurIPS 2023Data-Centric Learning from Unlabeled Graphs with Diffusion Model
4. NeurIPS 2023Diffused Redundancy in Pre-trained Representations
5. NeurIPS 2023Does progress on ImageNet transfer to real-world datasets?
6. NeurIPS 2023Doubly Robust Augmented Transfer for Meta-Reinforcement Learning
7. NeurIPS 2023Easy Bayesian Transfer Learning with Informative Priors
8. NeurIPS 2023Enhancing Knowledge Transfer for Task Incremental Learning with Data-free Subnetwork
9. NeurIPS 2023Fast Trainable Projection for Robust Fine-tuning
10. NeurIPS 2023ForkMerge: Mitigating Negative Transfer in Auxiliary-Task Learning
11. NeurIPS 2023Graph-Structured Gaussian Processes for Transferable Graph Learning
12. NeurIPS 2023Holistic Transfer: Towards Non-Disruptive Fine-Tuning with Partial Target Data
13. NeurIPS 2023LART: Neural Correspondence Learning with Latent Regularization Transformer for 3D Motion Transfer
14. NeurIPS 2023LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning
15. NeurIPS 2023Make the U in UDA Matter: Invariant Consistency Learning for Unsupervised Domain Adaptation
16. NeurIPS 2023ReContrast: Domain-Specific Anomaly Detection via Contrastive Reconstruction
17. NeurIPS 2023Robust Knowledge Transfer in Tiered Reinforcement Learning
18. NeurIPS 2023Selectivity Drives Productivity: Efficient Dataset Pruning for Enhanced Transfer Learning
19. NeurIPS 2023To Stay or Not to Stay in the Pre-train Basin: Insights on Ensembling in Transfer Learning
20. NeurIPS 2023Transfer Learning with Affine Model Transformation
21. NeurIPS 2023Transportability for Bandits with Data from Different Environments
22. NeurIPS 2023URL: A Representation Learning Benchmark for Transferable Uncertainty Estimates
23. NeurIPS 2023VPGTrans: Transfer Visual Prompt Generator across LLMs

常见问题

2023–2026 年四大会议一共有多少篇深度学习 · transfer learning论文？

共 197 篇，按年份分别是 2023 年 56 篇、2024 年 44 篇、2025 年 43 篇、2026 年 54 篇。

NeurIPS 2026 有多少篇深度学习 · transfer learning论文？

NeurIPS 2026 有 18 篇深度学习 · transfer learning论文，上一届是 16 篇。

ICLR 2026 有多少篇深度学习 · transfer learning论文？

ICLR 2026 有 9 篇深度学习 · transfer learning论文，上一届是 9 篇。

ICML 2026 有多少篇深度学习 · transfer learning论文？

ICML 2026 有 13 篇深度学习 · transfer learning论文，上一届是 10 篇。

CVPR 2026 有多少篇深度学习 · transfer learning论文？

CVPR 2026 有 14 篇深度学习 · transfer learning论文，上一届是 8 篇。

哪个会议的深度学习 · transfer learning论文最多？

NeurIPS，2023–2026 年共 71 篇。