Cover Image

Cross-Model Transfer of Task Vectors via Few-Shot Orthogonal Alignment

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Kawamoto, Kazuhiko, Endo, Atsuhiro, Kera, Hiroshi
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Zero-Shot Textual Explanations via Translating Decision-Critical Features
by: Yamauchi, Toshinori, et al.
Published: (2025)

Zero-Shot Faithful Textual Explanations via Directional-Derivative Influence on Predictions
by: Yamauchi, Toshinori, et al.
Published: (2026)

Explaining Object Detectors via Collective Contribution of Pixels
by: Yamauchi, Toshinori, et al.
Published: (2024)

Robust Human Trajectory Prediction via Self-Supervised Skeleton Representation Learning
by: Arashima, Taishu, et al.
Published: (2026)

Adapter Merging with Centroid Prototype Mapping for Scalable Class-Incremental Learning
by: Fukuda, Takuma, et al.
Published: (2024)

Low-Quality Image Detection by Hierarchical VAE
by: Nanaumi, Tomoyasu, et al.
Published: (2024)

Fourier Analysis on Robustness of Graph Convolutional Neural Networks for Skeleton-based Action Recognition
by: Tanaka, Nariki, et al.
Published: (2023)

Learning Moderately Input-Sensitive Functions: A Case Study in QR Code Decoding
by: Yoda, Kazuki, et al.
Published: (2025)

Identifying Important Group of Pixels using Interactions
by: Sumiyasu, Kosuke, et al.
Published: (2024)

Adversarially Trained Object Detector for Unsupervised Domain Adaptation
by: Fujii, Kazuma, et al.
Published: (2021)

Towards Viewpoint-Robust End-to-End Autonomous Driving with 3D Foundation Model Priors
by: Hashimoto, Hiroki, et al.
Published: (2026)

Undertrained Image Reconstruction for Realistic Degradation in Blind Image Super-Resolution
by: Ito, Ru, et al.
Published: (2025)

Matching Semantically Similar Non-Identical Objects
by: Marumo, Yusuke, et al.
Published: (2024)

Causal Disentanglement and Cross-Modal Alignment for Enhanced Few-Shot Learning
by: Jiang, Tianjiao, et al.
Published: (2025)

FlowSlider: Training-Free Continuous Image Editing via Fidelity-Steering Decomposition
by: Endo, Taichi, et al.
Published: (2026)

Cross-Modal Prototype Alignment and Mixing for Training-Free Few-Shot Classification
by: Goswami, Dipam, et al.
Published: (2026)

MindShot: A Few-Shot Brain Decoding Framework via Transferring Cross-Subject Prior and Distilling Frequency Domain Knowledge
by: Jiang, Shuai, et al.
Published: (2024)

Few-Shot Fruit Segmentation via Transfer Learning
by: James, Jordan A., et al.
Published: (2024)

GeoTransfer : Generalizable Few-Shot Multi-View Reconstruction via Transfer Learning
by: Jena, Shubhendu, et al.
Published: (2024)

Few-Shot Learning from Gigapixel Images via Hierarchical Vision-Language Alignment and Modeling
by: Wong, Bryan, et al.
Published: (2025)

OrCo: Towards Better Generalization via Orthogonality and Contrast for Few-Shot Class-Incremental Learning
by: Ahmed, Noor, et al.
Published: (2024)

Activation Reward Models for Few-Shot Model Alignment
by: Chai, Tianning, et al.
Published: (2025)

MomentsNeRF: Leveraging Orthogonal Moments for Few-Shot Neural Rendering
by: AlMughrabi, Ahmad, et al.
Published: (2024)

Improving CLIP Adaptation by Breaking Tail Alignment for Source-Free Cross-Domain Few-Shot Learning
by: Yi, Shuai, et al.
Published: (2026)

Enhancing Generalized Few-Shot Semantic Segmentation via Effective Knowledge Transfer
by: Chen, Xinyue, et al.
Published: (2024)

Bayesian Cross-Modal Alignment Learning for Few-Shot Out-of-Distribution Generalization
by: Zhu, Lin, et al.
Published: (2025)

MVP-Shot: Multi-Velocity Progressive-Alignment Framework for Few-Shot Action Recognition
by: Qu, Hongyu, et al.
Published: (2024)

Few-Shot Synthetic Data Generation with Diffusion Models for Downstream Vision Tasks
by: Dushenev, Daniil, et al.
Published: (2026)

Cross-Domain Few-Shot Semantic Segmentation via Doubly Matching Transformation
by: Chen, Jiayi, et al.
Published: (2024)

Cross-Domain Few-Shot Segmentation via Multi-view Progressive Adaptation
by: Nie, Jiahao, et al.
Published: (2026)

Cross-Modal Few-Shot Learning: a Generative Transfer Learning Framework
by: Yang, Zhengwei, et al.
Published: (2024)

FROMAT: Multiview Material Appearance Transfer via Few-Shot Self-Attention Adaptation
by: Kompanowski, Hubert, et al.
Published: (2025)

HAAF: Hierarchical Adaptation and Alignment of Foundation Models for Few-Shot Pathology Anomaly Detection
by: Yang, Chunze, et al.
Published: (2026)

Video-to-Task Learning via Motion-Guided Attention for Few-Shot Action Recognition
by: Guo, Hanyu, et al.
Published: (2024)

Adversarial Training from Mean Field Perspective
by: Kumano, Soichiro, et al.
Published: (2025)

Adversarially Pretrained Transformers May Be Universally Robust In-Context Learners
by: Kumano, Soichiro, et al.
Published: (2025)

Random Registers for Cross-Domain Few-Shot Learning
by: Yi, Shuai, et al.
Published: (2025)

Exploring Cross-Modal Flows for Few-Shot Learning
by: Jiang, Ziqi, et al.
Published: (2025)

Theoretical Understanding of Learning from Adversarial Perturbations
by: Kumano, Soichiro, et al.
Published: (2024)

Wide Two-Layer Networks can Learn from Adversarial Perturbations
by: Kumano, Soichiro, et al.
Published: (2024)