7 papers
Expertise-Based Developer Assignment for Long-Term Software Components in Open-Source Projects
Faheem Ullah, Babar Shah, William Shanks +2
Open-source software development through GitHub has enabled countless software projects to be developed by developers from across the world. Assigning the right task to the right d…
What If We Allocate Test-Time Compute Adaptively?
Ahsan Bilal, Ahmed Mohsin, Muhammad Umer +4
Test-time compute scaling allocates inference computation uniformly, uses fixed sampling strategies, and applies verification only for reranking. In contrast, we propose a verifier…
Epistemic Uncertainty for Test-Time Discovery
Kainat Riaz, Muhammad Ahmed Mohsin, Ahsan Bilal +5
Automated scientific discovery using large language models relies on identifying genuinely novel solutions. Standard reinforcement learning penalizes high-variance mutations, which…
Towards Green Connectivity: An AI-Driven Mesh Architecture for Sustainable and Scalable Wireless Networks
Muhammad Ahmed Mohsin, Muhammad Jazib, Muhammad Saad +1
Traditional macro-cell and micro-cell infrastructures suffer from severe inefficiencies, with current macro-cell networks operating at less than 5 percent energy efficiency, leadin…
Uncertainty-Weighted Experience Replay for Continual MIMO Channel Prediction
Muhammad Jazib Qamar, Muhammad Hamza Nawaz, Messaoud Ahmed Ouameur +2
In dynamic wireless environments, accurate channel state information (CSI) prediction remains challenging due to non-stationary fading, mobility. This paper proposes an Uncertainty…
On the Fundamental Limits of LLMs at Scale
Muhammad Ahmed Mohsin, Muhammad Umer, Ahsan Bilal +13
Large Language Models (LLMs) have benefited enormously from scaling, yet these gains are bounded by five fundamental limitations: (1) hallucination, (2) context compression, (3) re…