6 papers
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…
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…
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,…
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…
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…
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…