Deep learning · transfer learning papers, 2023–2026

Key findings

• Deep learning · transfer learning fell from 56 papers in 2023 to 54 in 2026, so interest is cooling.
• NeurIPS publishes the most Deep learning · transfer learning work: 71 papers from 2023 to 2026, 36% of the four-venue total.
• The fastest-growing overlap is with Multimodal LLMs: papers tagged with both rose from 2 in 2023 to 5 in 2026.
• Among the 11 topics under Deep Learning, it ranks #11 by 2026 paper count; the fastest grower in the group, Diffusion Models, is up 4.1x versus 1.0x here.

Representative papers

Spread across years and venues so every edition shows up

• 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

All Deep learning · transfer learning papers

71 papers, page 1 of 2

1. NeurIPS 2026CLeaR: A Unified Framework for Resolving the Leakage–Degradation Dilemma in Style Transfer
2. NeurIPS 2026Counterfactual Debugging the World Model Transfer Gap
3. NeurIPS 2026Cross-Model KV Cache Transfer in LLM Families: A Closed-Form Linear Mapping for Prefill Reuse
4. NeurIPS 2026Emergent Misalignment as Data-Mediated Transfer
5. NeurIPS 2026Exploring MLLM-Diffusion Information Transfer with MetaCanvas
6. NeurIPS 2026Hyperparameter Transfer for Dense Associative Memories
7. NeurIPS 2026Information Parity for Code: The Scope of Transfer in Multilingual Code Models
8. NeurIPS 2026Learning Rate Transfer for Hybrid Transformer-SSM Architectures
9. NeurIPS 2026Learning Rate Transfer in Normalized Transformers
10. NeurIPS 2026Learning to Undo: Transfer Reinforcement Learning under State Space Transformations
11. NeurIPS 2026Model-Aware Tokenizer Transfer
12. NeurIPS 2026On the Effect of Token Correlations on Semantic Transfer in Transformers
13. NeurIPS 2026Phantom Transfer: Data Poisoning can Survive Data-Level Defences
14. NeurIPS 2026Shared Truth: Emergent Truth Properties in Large Language Models via Heterogeneous Injection-based Transfer
15. NeurIPS 2026SkillOrchestra: Learning to Route Agents via Skill Transfer
16. NeurIPS 2026Towards Hyperparameter Transfer for Differentially Private Optimization
17. NeurIPS 2026Transfer Learning of Linear Regression with Multiple Pretrained Models: Benefiting from More Pretrained Models via Overparameterization Debiasing
18. NeurIPS 2026Voice "Cloning" Is Actually Style Transfer
19. NeurIPS 2025$\mu$PC: Scaling Predictive Coding to 100+ Layer Networks
20. NeurIPS 2025$\texttt{BetaConform}$: Efficient MAP Estimation of LLM Ensemble Judgment Performance with Prior Transfer
21. NeurIPS 2025Asymmetric Duos: Sidekicks Improve Uncertainty
22. NeurIPS 2025Co-Regularization Enhances Knowledge Transfer in High Dimensions
23. NeurIPS 2025Don't be lazy: CompleteP enables compute-efficient deep transformers
24. NeurIPS 2025Extrapolation by Association: Length Generalization Transfer In Transformers
25. NeurIPS 2025How Classifier Features Transfer to Downstream: An Asymptotic Analysis in a Two-Layer Model
26. NeurIPS 2025One for All: Universal Topological Primitive Transfer for Graph Structure Learning
27. NeurIPS 2025Order-Level Attention Similarity Across Language Models: A Latent Commonality
28. NeurIPS 2025Pairwise Optimal Transports for Training All-to-All Flow-Based Condition Transfer Model
29. NeurIPS 2025Provable Sample-Efficient Transfer Learning Conditional Diffusion Models via Representation Learning
30. NeurIPS 2025Transfer Faster, Price Smarter: Minimax Dynamic Pricing under Cross-Market Preference Shift
31. NeurIPS 2025Transfer Learning for Benign Overfitting in High-Dimensional Linear Regression
32. NeurIPS 2025Transfer Learning on Edge Connecting Probability Estimation Under Graphon Model
33. NeurIPS 2025Universal Cross-Tokenizer Distillation via Approximate Likelihood Matching
34. NeurIPS 2025Wasserstein Transfer Learning
35. NeurIPS 2024Learning Transferable Features for Implicit Neural Representations
36. NeurIPS 2024Model-Based Transfer Learning for Contextual Reinforcement Learning
37. NeurIPS 2024On the Benefits of Public Representations for Private Transfer Learning under Distribution Shift
38. NeurIPS 2024On the Surprising Effectiveness of Attention Transfer for Vision Transformers
39. NeurIPS 2024Revealing Distribution Discrepancy by Sampling Transfer in Unlabeled Data
40. NeurIPS 2024SHMT: Self-supervised Hierarchical Makeup Transfer via Latent Diffusion Models
41. NeurIPS 2024SubjECTive-QA: Measuring Subjectivity in Earnings Call Transcripts' QA Through Six-Dimensional Feature Analysis
42. NeurIPS 2024The Impact of Geometric Complexity on Neural Collapse in Transfer Learning
43. NeurIPS 2024The Limits of Transfer Reinforcement Learning with Latent Low-rank Structure
44. NeurIPS 2024Transfer Learning for Diffusion Models
45. NeurIPS 2024Transfer Learning for Latent Variable Network Models
46. NeurIPS 2024Transfer Learning with Informative Priors: Simple Baselines Better than Previously Reported
47. NeurIPS 2024Transfer Q-star : Principled Decoding for LLM Alignment
48. NeurIPS 2024Universality in Transfer Learning for Linear Models
49. NeurIPS 2023Combining Behaviors with the Successor Features Keyboard
50. NeurIPS 2023Conditional Adapters: Parameter-efficient Transfer Learning with Fast Inference

FAQ

How many Deep learning · transfer learning papers were published at NeurIPS, ICLR, ICML and CVPR from 2023 to 2026?

197 in total: 56 in 2023, 44 in 2024, 43 in 2025, 54 in 2026.

How many Deep learning · transfer learning papers are at NeurIPS 2026?

NeurIPS 2026 has 18 Deep learning · transfer learning papers, versus 16 the year before.

How many Deep learning · transfer learning papers are at ICLR 2026?

ICLR 2026 has 9 Deep learning · transfer learning papers, versus 9 the year before.

How many Deep learning · transfer learning papers are at ICML 2026?

ICML 2026 has 13 Deep learning · transfer learning papers, versus 10 the year before.

How many Deep learning · transfer learning papers are at CVPR 2026?

CVPR 2026 has 14 Deep learning · transfer learning papers, versus 8 the year before.

Which conference publishes the most Deep learning · transfer learning papers?

NeurIPS, with 71 papers from 2023 to 2026.