Nurbek Tastan

According to our database, Nurbek Tastan authored at least 17 papers between 2019 and 2026.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2026

Data-Free Client Contribution Estimation via Logit Maximization for Federated Learning.

Asim Ukaye, Nurbek Tastan, Mubarak G. Abdu-Aguye, Karthik Nandakumar

CoRR, May, 2026

Response-Conditioned Parallel-to-Sequential Orchestration for Multi-Agent Systems.

Nurbek Tastan, Alex Iacob, Lorenzo Sani, Meghdad Kurmanji, Nicholas D. Lane, Samuel Horvath, Karthik Nandakumar

CoRR, May, 2026

Data-Free Contribution Estimation in Federated Learning using Gradient von Neumann Entropy.

Asim Ukaye, Mubarak G. Abdu-Aguye, Nurbek Tastan, Karthik Nandakumar

CoRR, April, 2026

MoSE: Mixture of Slimmable Experts for Efficient and Adaptive Language Models.

Nurbek Tastan, Stefanos Laskaridis, Karthik Nandakumar, Samuel Horvath

CoRR, February, 2026

2025

SPDMark: Selective Parameter Displacement for Robust Video Watermarking.

Samar Fares, Nurbek Tastan, Karthik Nandakumar

CoRR, December, 2025

Stochastic Self-Organization in Multi-Agent Systems.

Nurbek Tastan, Samuel Horvath, Karthik Nandakumar

CoRR, October, 2025

MOLM: Mixture of LoRA Markers.

Samar Fares, Nurbek Tastan, Noor Hussein, Karthik Nandakumar

CoRR, October, 2025

LoFT: Low-Rank Adaptation That Behaves Like Full Fine-Tuning.

Nurbek Tastan, Stefanos Laskaridis, Martin Takác, Karthik Nandakumar, Samuel Horváth

CoRR, May, 2025

CYCle: Choosing Your Collaborators Wisely to Enhance Collaborative Fairness in Decentralized Learning.

Nurbek Tastan, Samuel Horváth, Karthik Nandakumar

Trans. Mach. Learn. Res., 2025

Aequa: Fair Model Rewards in Collaborative Learning via Slimmable Networks.

Nurbek Tastan, Samuel Horváth, Karthik Nandakumar

Proceedings of the Forty-second International Conference on Machine Learning, 2025

A Framework for Double-Blind Federated Adaptation of Foundation Models.

Nurbek Tastan, Karthik Nandakumar

Proceedings of the IEEE/CVF International Conference on Computer Vision, 2025

FedPeWS: Personalized Warmup via Subnetworks for Enhanced Heterogeneous Federated Learning.

Nurbek Tastan, Samuel Horváth, Martin Takác, Karthik Nandakumar

Proceedings of the Conference on Parsimony and Learning, 2025

2024

A Coarse-to-Fine Pseudo-Labeling (C2FPL) Framework for Unsupervised Video Anomaly Detection.

Anas Al-Lahham, Nurbek Tastan, Muhammad Zaigham Zaheer, Karthik Nandakumar

Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2024

Redefining Contributions: Shapley-Driven Federated Learning.

Nurbek Tastan, Samar Fares, Toluwani Aremu, Samuel Horváth, Karthik Nandakumar

Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence, 2024

Collaborative Learning of Anomalies with Privacy (CLAP) for Unsupervised Video Anomaly Detection: A New Baseline.

Anas Al-lahham, Muhammad Zaigham Zaheer, Nurbek Tastan, Karthik Nandakumar

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024

2023

CaPriDe Learning: Confidential and Private Decentralized Learning Based on Encryption-Friendly Distillation Loss.

Nurbek Tastan, Karthik Nandakumar

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

2019

Burglary Detection Framework for House Crime Control.

Nurbek Tastan, Abdul Razaque, Mohamed Ben Haj Frej, Amanzholova Saule Toksanovna, Raouf M. Ganda, Fathi H. Amsaad

Proceedings of the 19th International Conference on Computational Science and Its Applications, 2019