papers

Publications (9)

eess.SP2021

A Fast Graph Kernel Based Classification Method for Wireless Link Scheduling on Riemannian Manifold

Rashed Shelim, Ahmed S. Ibrahim

In this paper, we propose a novel graph kernel method for the wireless link scheduling problem in device-to-device (D2D) networks on Riemannian manifold. The link scheduling proble…

cs.LG2025

DMWM: Dual-Mind World Model with Long-Term Imagination

Lingyi Wang, Rashed Shelim, Walid Saad +1

Imagination in world models is crucial for enabling agents to learn long-horizon policy in a sample-efficient manner. Existing recurrent state-space model (RSSM)-based world models…

cs.IT2025

A Theoretically-Grounded Codebook for Digital Semantic Communications

Lingyi Wang, Rashed Shelim, Walid Saad +1

The use of a learnable codebook provides an efficient way for semantic communications to map vector-based high-dimensional semantic features onto discrete symbol representations re…

eess.SY2024

Fast Geometric Learning of MIMO Signal Detection over Grassmannian Manifolds

Rashed Shelim, Walid Saad, Naren Ramakrishnan

Domain or statistical distribution shifts are a key staple of the wireless communication channel, because of the dynamics of the environment. Deep learning (DL) models for detectin…

cs.AI2026

MetaMind: General and Cognitive World Models in Multi-Agent Systems by Meta-Theory of Mind

Lingyi Wang, Rashed Shelim, Walid Saad +1

A major challenge for world models in multi-agent systems is to understand interdependent agent dynamics, predict interactive multi-agent trajectories, and plan over long horizons…

cs.IT2025

Dual-Mind World Models: A General Framework for Learning in Dynamic Wireless Networks

Lingyi Wang, Rashed Shelim, Walid Saad +1

Despite the popularity of reinforcement learning (RL) in wireless networks, existing approaches that rely on model-free RL (MFRL) and model-based RL (MBRL) are data inefficient and…

cs.CL2025

When can isotropy help adapt LLMs' next word prediction to numerical domains?

Rashed Shelim, Shengzhe Xu, Walid Saad +1

Vector representations of contextual embeddings learned by pre-trained large language models (LLMs) are effective in various downstream tasks in numerical domains such as time seri…

cs.MA2025

Dynamic Strategy Adaptation in Multi-Agent Environments with Large Language Models

Shaurya Mallampati, Rashed Shelim, Walid Saad +1

Large language models (LLMs) demonstrate strong reasoning abilities across mathematical, strategic, and linguistic tasks, yet little is known about how well they reason in dynamic,…

cs.AI2025

World Model-Based Learning for Long-Term Age of Information Minimization in Vehicular Networks

Lingyi Wang, Rashed Shelim, Walid Saad +1

Traditional reinforcement learning (RL)-based learning approaches for wireless networks rely on expensive trial-and-error mechanisms and real-time feedback based on extensive envir…