activity
20242026
collaborators

5 papers

cs.AI2026

ProgRouter: Online Progress-Guided Orchestration for Multi-Agent LLM Workflows under Quality-Cost Tradeoffs

Songyuan Li, Ahmed M. Abdelmoniem, Shiqiang Wang

Multi-agent large language model (LLM) workflows have emerged as a powerful paradigm for solving complex, open-ended tasks through collaborative reasoning among specialized LLM age…

cs.LG2026

HASA: Subnet Allocation for Compute-Constrained Model-Heterogeneous Federated Learning

Amir Hossein Shahdadian, Ahmed M. Abdelmoniem, Mahdi Taheri +2

Edge services increasingly use federated learning to personalize on-device models while keeping sensitive data local. In practice, deployments must handle heterogeneity in both cli…

cs.LG2026

BLOSSOM: Block-wise Federated Learning Over Shared and Sparse Observed Modalities

Pranav M R, Jayant Chandwani, Ahmed M. Abdelmoniem +1

Multimodal federated learning (FL) is essential for real-world applications such as autonomous systems and healthcare, where data is distributed across heterogeneous clients with v…

cs.CR2025

AdRo-FL: Informed and Secure Client Selection for Federated Learning in the Presence of Adversarial Aggregator

Md. Kamrul Hossain, Walid Aljoby, Anis Elgabli +2

Federated Learning (FL) enables collaborative learning without exposing clients' data. While clients only share model updates with the aggregator, studies reveal that aggregators c…

cs.LG2024

A Communication and Computation Efficient Fully First-order Method for Decentralized Bilevel Optimization

Min Wen, Chengchang Liu, Ahmed Abdelmoniem +2

Bilevel optimization, crucial for hyperparameter tuning, meta-learning and reinforcement learning, remains less explored in the decentralized learning paradigm, such as decentraliz…