The 5th Workshop on Federated Learning for Computer Vision
DynaMu: Loss-Guided Adaptive Proximal Regularization for Federated Learning-
[pdf]
[bibtex]@InProceedings{Hajarizadeh_2026_CVPR, author = {Hajarizadeh, Armaan and Gupta, Suyash}, title = {DynaMu: Loss-Guided Adaptive Proximal Regularization for Federated Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {3321-3329} }
Data-Free Contribution Estimation in Federated Learning using Gradient von Neumann Entropy-
[pdf]
[supp]
[bibtex]@InProceedings{Ukaye_2026_CVPR, author = {Ukaye, Asim and Abdu-Aguye, Mubarak and Tastan, Nurbek and Nandakumar, Karthik}, title = {Data-Free Contribution Estimation in Federated Learning using Gradient von Neumann Entropy}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {3369-3378} }
FedPoisonTTP: A Threat Model and Poisoning Attack for Federated Test-Time Personalization-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Iftee_2026_CVPR, author = {Iftee, Md. Akil Raihan and Hasan, Syed Md. Ahnaf and Ali, Amin Ahsan and Rahman, A K M Mahbubur and Mistry, Sajib and Krishna, Aneesh}, title = {FedPoisonTTP: A Threat Model and Poisoning Attack for Federated Test-Time Personalization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {3330-3339} }
UniFed-LoRA: Exploiting Semantic Task Correlation for Heterogeneous Multimodal Federated Fine-Tuning-
[pdf]
[supp]
[bibtex]@InProceedings{Milasheuski_2026_CVPR, author = {Milasheuski, Usevalad and Lu, Charles and Chari, Pradyumna and Nicoli, Monica and Savazzi, Stefano and Raskar, Ramesh}, title = {UniFed-LoRA: Exploiting Semantic Task Correlation for Heterogeneous Multimodal Federated Fine-Tuning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {3349-3358} }
DART: A Server-side Plug-in for Resource-efficient Robust Federated Learning-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Bekdache_2026_CVPR, author = {Bekdache, Omar and Shanbhag, Naresh}, title = {DART: A Server-side Plug-in for Resource-efficient Robust Federated Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {3301-3311} }
DALSE: Drift-Aware Latent State Estimation for Robust Federated Learning under Dynamic Participation-
[pdf]
[bibtex]@InProceedings{Chang_2026_CVPR, author = {Chang, Ching-Hwa and Lee, Ming-Lun and Lin, Cheng-Kuan and Tseng, Yu-Chee}, title = {DALSE: Drift-Aware Latent State Estimation for Robust Federated Learning under Dynamic Participation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {3312-3320} }
Conditional Imputation for Within-Modality Missingness in Multi-Modal Federated Learning-
[pdf]
[arXiv]
[bibtex]@InProceedings{Zheng_2026_CVPR, author = {Zheng, Wugeng and Kan, Ziwen and Wang, Katie and Chen, Chen and Wang, Song}, title = {Conditional Imputation for Within-Modality Missingness in Multi-Modal Federated Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {3379-3388} }
SCOPE: Shared Content Orchestration of Parameter-Efficient Experts for Federated Domain Generalization-
[pdf]
[supp]
[bibtex]@InProceedings{Soliman_2026_CVPR, author = {Soliman, Mahmoud and Radwan, Ahmed and Abdelaziz, Omar and Shehata, Mohamed S.}, title = {SCOPE: Shared Content Orchestration of Parameter-Efficient Experts for Federated Domain Generalization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {3359-3368} }
FedSIR: Spectral Client Identification and Relabeling for Federated Learning with Noisy Labels-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Gholami_2026_CVPR, author = {Gholami, Sina and Ali, Abudlmoneam and Haghighi, Tania and Arafa, Ahmed and Alam, Minhaj Nur}, title = {FedSIR: Spectral Client Identification and Relabeling for Federated Learning with Noisy Labels}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {3340-3348} }

