Transfer Learning

Follow this topic Ask about this topic

Transfer learning asks how a model trained on one task or domain can help with another, reducing the need for target-specific data and computation. Common approaches include pretraining followed by fine-tuning or parameter-efficient adapters, feature alignment for domain shifts, and knowledge transfer through distillation, model merging, or shared representations. Evaluations span zero-shot and few-shot transfer, cross-domain benchmarks in vision and language, and adaptation in settings such as clinical data, robotics, and scientific modeling. A central tension is that transferred knowledge can improve accuracy and sample efficiency or cause negative transfer; predicting when it will help, and separating reusable knowledge from dataset or architecture effects, remains difficult.

Latest papers

422 papers62 papers in the last four weeks, up 29% on the four weeks before. 0.4% of all new papers.

CapVector: Learning Transferable Capability Vectors in Parametric Space for Vision-Language-Action Models
May 11, 2026Wenxuan Song, Han Zhao, Fuhao Li +7Task Vectors VLM Adaptation
1HKUST (GZ) · 2Zhejiang University · 3Westlake University +2
CORTEG: Foundation Models Enable Cross-Modality Representation Transfer from Scalp to Intracranial Brain Recordings
May 11, 2026Liuyin Yang, Qiang Sun, Bob Van Dyck +2Brain-Computer Interfaces Neural Decoding
Laboratory for Neuro- & Psychophysiology, Department of Neurosciences, KU Leuven
Cross-Family Universality of Behavioral Axes via Anchor-Projected Representations
May 11, 2026Su-Hyeon Kim, Yo-Sub HanLLM Interpretability Transfer Learning
Department of Artificial Intelligence Yonsei University Seoul, South Korea · Department of Computer Science Yonsei University Seoul, South Korea
SeePhys Pro: Diagnosing Modality Transfer and Blind-Training Effects in Multimodal RLVR for Physics Reasoning
May 10, 2026Kun Xiang, Terry Jingchen Zhang, Zirong Liu +15Cross-Modal Learning Multimodal Grounding
Sun Yat-sen University · ETH Zurich · Huawei Technologies Ltd. +1
Transfer Learning of Multiobjective Indirect Low-Thrust Trajectories Using Diffusion Models and Markov Chain Monte Carlo
May 9, 2026Jannik Graebner, Ryne BeesonMarkov Chain Monte Carlo Trajectory Optimization
PhD Candidate, Department of Mechanical and Aerospace Engineering, Princeton University, NJ, USA. · Assistant Professor, Department of Mechanical and Aerospace Engineering, Princeton University, NJ, USA.
Quantum Transfer Learning Shows Improved Robustness in Low-Data Regimes
May 9, 2026Li-An Lo, Li-Yi Hsu, Hsien-Yi HsiehQuantum Machine Learning Transfer Learning
Department of Engineering Science, National Cheng Kung University, Tainan 701401, Taiwan · Department of Physics, Chung Yuan Christian University, Chungli 32081, Taiwan · Physics Division, National Center for Theoretical Sciences, Taipei 106319, Taiwan +1
Reducing Annotation Burden for Femoral Cartilage Segmentation in Knee MRI via Cross-Sequence Transfer Learning
May 9, 2026Francesco Chiumento, Gianluigi Crimi, Elisa Moretta +7Magnetic Resonance Imaging Transfer Learning
School of Electronic Engineering, Dublin City University, Dublin, Ireland · Bioengineering and Computing Laboratory, IRCCS Istituto Ortopedico Rizzoli, Bologna, Italy · Dipartimento di Scienze Mediche e Chirurgiche (DIMEC), Alma Mater Studiorum – Università di Bologna, Bologna, Italy +4
CrystalREPA: Transferring Physical Priors from Universal MLIPs to Crystal Generative Models
May 9, 2026Chengqian Zhang, Yucheng Jin, Duo Zhang +2Transfer Learning Crystal Structure Generation
AI for Science Institute, Beijing, China · Center for Data Science, Peking University, Beijing, China · LMAM and School of Mathematical Sciences, Peking University, Beijing, China +3
From pre-training to downstream performance: Does domain-specific pre-training make sense?
May 9, 2026Felix KronesSelf-Supervised Pre-Training Domain-Adaptive Pretraining
Oxford Internet Institute, University of Oxford, Oxford, UK
CAST: Channel-Aware Spatial Transfer Learning with Pseudo-Image Radar for Sign Language Recognition
May 9, 2026Md. Shakhoyat Rahman Shujon, Sheikh Md. Galib Mahim, Md. Milon Islam +4Millimeter-Wave Radar mmWave Radar Sensing
Department of Computer Science and Engineering, Khulna University of Engineering & Technology · Department of Electrical and Computer Engineering, University of Waterloo · Department of Electrical and Computer Engineering, Texas A&M University +2
Transfer Learning for Dead Fuel Moisture Prediction Using Time-Warping Recurrent Neural Networks
May 8, 2026Jonathon Hirschi, Jan Mandel, Adam KochanskiRecurrent Neural Networks Transfer Learning
Department of Mathematical and Statistical Sciences, University of Colorado Denver, Colorado · Department of Meteorology and Climate Science, Wildfire Interdisciplinary Research Center, San Jose State University, San Jose, California
Priming: Hybrid State Space Models From Pre-trained Transformers
May 8, 2026Aditya Chattopadhyay, Elvis Nunez, Prannay Kaul +6State Space Models Long-Context Language Model Inference
AWS Agentic AI
What Cohort INRs Encode and Where to Freeze Them
May 8, 2026Vasiliki Sideri-Lampretsa, Sophie Starck, Robbie Holland +2Implicit Neural Representations Mechanistic Interpretability
Chair of AI in Healthcare and Medicine, Technical University of Munich, Germany · TUM University Hospital, Munich, Germany · Stanford Center for Artificial Intelligence in Medicine and Imaging, Stanford University, Stanford, CA, USA +3
Transfer Learning Across Fast- and Full-Simulation Domains in High-Energy Physics
May 8, 2026Matthias Schott, Lucie FlekDomain Adaptation High-Energy Physics
Institute of Physics, University of Bonn, Germany · Bonn-Aachen International Center for Information Technology (b-it), University of Bonn, Germany
Emergent Symbolic Structure in Health Foundation Models: Extraction, Alignment, and Cross-Modal Transfer
May 8, 2026Gajendra Katuwal, Advait Koparkar, Salar Abbaspourazad +2Cross-Modal Learning Representation Learning
Apple
Pretraining Induces a Reusable Spectral Basis for Downstream Task Adaptation
May 8, 2026Junjie Yu, Yue Wang, Zihan Deng +3Transfer Learning Parameter-Efficient Fine-Tuning
Department of Biomedical Engineering, Southern University of Science and Technology · Department of Psychology, The University of Hong Kong
Direct-to-Event Spiking Neural Network Transfer
May 8, 2026Nhan Trong Luu, Duong Trung Luu, Pham Ngoc Nam +1Efficient Neural Network Inference Spiking Neural Networks
College of ICT, Can Tho University, Vietnam · CECS, VinUniversity, Hanoi, Vietnam · Center of Digital Transformation and Communication, Can Tho University, Vietnam +1
Closed-Form Linear-Probe Dataset Distillation for Pre-trained Vision Models
May 8, 2026Bincheng Peng, Guang Li, Ping Liu +2Linear Probing Dataset Distillation
Hokkaido University · University of Nevada, Reno
Attention Transfer Is Not Universally Effective for Vision Transformers
May 8, 2026Huaiyuan Qin, Muli Yang, Gabriel James Goenawan +4Self-Attention Vision Transformer
Institute of Advanced Intelligence and Computing (IAIC), A*STAR, Singapore · School of Artificial Intelligence, Sichuan University · School of Automation and Intelligent Sensing, Shanghai Jiao Tong University
Tumor-aware augmentation with task-guided attention analysis improves rectal cancer segmentation from magnetic resonance images
May 6, 2026Aneesh Rangnekar, Joao Miranda, Natally Horvat +13Cross-Modal Learning Cross-Modality Medical Image Segmentation
Department of Medical Physics, Memorial Sloan Kettering Cancer Center, 1275 York Avenue, New York, NY, 10065, USA · Department of Radiology, Memorial Sloan Kettering Cancer Center, 1275 York Avenue, New York, NY, 10065, USA · Department of Radiation Oncology, Memorial Sloan Kettering Cancer Center, 1275 York Avenue, New York, NY, 10065, USA +2
Bridging Input Feature Spaces Towards Graph Foundation Models
May 6, 2026Moshe Eliasof, Krishna Sri Ipsit Mantri, Beatrice Bevilacqua +2Graph Representation Learning Transfer Learning
University of Cambridge · Ben-Gurion University of the Negev · Purdue University
Learngene Search Across Multiple Datasets for Building Variable-Sized Models
May 6, 2026Boyu Shi, Junbo Zhou, Chang Liu +3Transfer Learning Neural Architecture Search
School of Computer Science and Engineering, Southeast University, Nanjing, China · Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications (Southeast University), Ministry of Education, China
Digital Image Forgery Detection Using Transfer Learning
May 4, 2026Fatma Betul Buyuk, Gozde Karatas Baydogmus, Ali Buldu +2Image Forgery Detection Digital Image Forensics
Marmara University, Department of Computer Engineering, Istanbul, TURKEY · Loyola University Chicago, Department of Computer Science, Chicago, USA · Biruni University, Department of Computer Engineering, Istanbul, TURKEY
Demographic-Aware Transfer Learning for Sleep Stage Classification in Clinical Polysomnography
May 4, 2026S M Asif Hossain, Shruti KshirsagarSleep Stage Classification Fine-Tuning
School of Computing, Wichita State University, Wichita, Kansas, USA
Personalized Digital Health Modeling with Adaptive Support Users
May 3, 2026Zhongqi Yang, Mahkameh Rasouli, Neda Mohseni +3Transfer Learning User Modeling
Department of Computer Science, University of California, Irvine · Sue & Bill Gross School of Nursing, University of California, Irvine · Thrive AI Health +1
Chebyshev-Augmented One-Shot Transfer Learning for PINNs on Nonlinear Differential Equations
May 2, 2026Yiqi Rao, Pavlos ProtopapasPDE Solving Transfer Learning
Harvard University
Dynamics Distillation for Efficient and Transferable Control Learning
May 2, 2026Xunjiang Gu, Kashyap Chitta, Mahsa Golchoubian +2Vehicle Dynamics Transfer Learning
University of Toronto · Vector Institute · NVIDIA +1
Developing a Strong Pre-Trained Base Model for Plant Leaf Disease Classification
May 2, 2026David J. RichterPlant Disease Classification Transfer Learning
Department of Artiﬁcial Intelligence Convergence Graduate School, Chonnam National University
Borrowed Geometry: Cross-Distribution Head-Importance Fingerprints of Frozen Pretrained Gemma 4 31B
May 1, 2026Abay BektursunCross-Modal Learning Attention Head Analysis
Independent research
When Continual Learning Moves to Memory: A Study of Experience Reuse in LLM Agents
Apr 29, 2026Qisheng Hu, Quanyu Long, Wenya WangContinual Learning for LLM Agents LLM Agent Memory
Nanyang Technological University

May 11, 2026J/K move · Enter open · S save

CapVector: Learning Transferable Capability Vectors in Parametric Space for Vision-Language-Action Models

Wenxuan Song, Han Zhao, Fuhao Li, Ziyang Zhou+6

1HKUST (GZ) · 2Zhejiang University · 3Westlake University+2

Task Vectors VLM Adaptation Transfer Learning Vision-Language-Action Models Model Merging

Open paper AskPDF arXiv

This paper proposes a novel approach to address the challenge that pretrained VLA models often fail to effectively improve performance and reduce adaptation costs during standard supervised finetuning (SFT). Some advanced finetuning methods with auxiliary training objectives can improve performance and reduce the number of convergence steps. However, they typically incur significant computational overhead due to the additional losses from auxiliary objectives. To simultaneously achieve the enhanced capabilities of auxiliary training with the simplicity of standard SFT, we decouple the two objectives of auxiliary-objective SFT within the parameter space, namely, enhancing general capabilities and fitting task-specific action distributions. To deliver the goal, we only need to train the model to converge on a small-scale task set using two distinct training strategies, resulting in two finetuned models. The parameters' difference between the two models can then be interpreted as capability vectors provided by auxiliary objectives. These vectors are then merged with pretrained parameters to form a capability-enhanced meta model. Moreover, when standard SFT is augmented with a lightweight orthogonal regularization loss, the merged model attains performance comparable to auxiliary finetuned baselines with reduced computational overhead. Internal and external experiments demonstrate that our capability vectors (1) are effective and versatile across diverse models, (2) can generalize to novel environments and embodiments out of the box.