6 citations · 11 across the 16 of their papers we have counts for
16 papers
COMED: The Missing Middle Between Routing and Collaboration in Multi-LLM Inference
Norah Alballa, Wenxuan Zhang, Salma Kharrat +4
No single Large Language Model (LLM) is uniformly reliable across queries, motivating multi-model inference systems that either route among models or combine their outputs. However…
Affix Cache for Diffusion Large Language Models
Kaihua Liang, An Zhong, Xin Tan +4
Diffusion Large Language Models (DLLMs) enable non-autoregressive decoding, but efficient inference support remains immature: unlike autoregressive models, whose requests reuse a s…
Separating Clicks from Baits: Using Large Language Models to Detect Misleading YouTube Thumbnails
Wajiha Naveed, Muhammad Muneeb Pervez, Zaeem Mohtashim Khan +2
Misleading video thumbnails on platforms like YouTube are a pervasive problem, undermining user trust and platform integrity. This paper proposes a novel multi-modal detection pipe…
Efficient and Adaptable Detection of Malicious LLM Prompts via Bootstrap Aggregation
Shayan Ali Hassan, Tao Ni, Zaeem Mohtashim Khan +2
Large Language Models have demonstrated remarkable capabilities in natural language understanding. However, they remain susceptible to malicious prompts that induce unsafe or polic…
MAESTRO: Multi-Agent Evaluation Suite for Testing, Reliability, and Observability
Tie Ma, Yixi Chen, Vaastav Anand +8
We present MAESTRO, an evaluation suite for the testing, reliability, and observability of LLM-based MAS. MAESTRO standardizes MAS configuration and execution through a unified int…
From Crawled to Published: A Publisher-Controlled Web Architecture for an AI-Native Internet
Yixi Chen, Muhammad Bilal, Zafar Qazi +4
AI agents, not humans, are becoming the web's primary consumers, yet the web still ships content structured for human browsing, with no native way for publishers to expose the sema…
DMAS-Forge: A Framework for Transparent Deployment of AI Applications as Distributed Systems
Alessandro Cornacchia, Vaastav Anand, Muhammad Bilal +2
Agentic AI applications increasingly rely on multiple agents with distinct roles, specialized tools, and access to memory layers to solve complex tasks -- closely resembling servic…
Scaling Truth: The Confidence Paradox in AI Fact-Checking
Ihsan A. Qazi, Zohaib Khan, Abdullah Ghani +7
The rise of misinformation underscores the need for scalable and reliable fact-checking solutions. Large language models (LLMs) hold promise in automating fact verification, yet th…
ThumbnailTruth: A Multi-Modal LLM Approach for Detecting Misleading YouTube Thumbnails Across Diverse Cultural Settings
Wajiha Naveed, Zartash Afzal Uzmi, Zafar Ayyub Qazi
Misleading video thumbnails on platforms like YouTube are a pervasive problem, undermining user trust and platform integrity. This paper proposes a novel multi-modal detection pipe…
TweakLLM: A Routing Architecture for Dynamic Tailoring of Cached Responses
Muhammad Taha Cheema, Abeer Aamir, Khawaja Gul Muhammad +3
Large Language Models (LLMs) process millions of queries daily, making efficient response caching a compelling optimization for reducing cost and latency. However, preserving relev…
Semantic Caching for Improving Web Affordability
Hafsa Akbar, Danish Athar, Muhammad Ayain Fida Rana +4
The rapid growth of web content has led to increasingly large webpages, posing significant challenges for Internet affordability, especially in developing countries where data cost…
Warping the Edge: Where Instant Mobility in 5G Meets Stateful Applications
Mukhtiar Ahmad, Faaiq Bilal, Mutahar Ali +5
Edge computing is considered a key paradigm for supporting real-time applications over 5G networks, as hosting applications at the network edge can substantially reduce delays. A s…
Rethinking Image Compression on the Web with Generative AI
Shayan Ali Hassan, Danish Humair, Ihsan Ayyub Qazi +1
The rapid growth of the Internet, driven by social media, web browsing, and video streaming, has made images central to the Web experience, resulting in significant data transfer a…
FedPrune: Towards Inclusive Federated Learning
Muhammad Tahir Munir, Muhammad Mustansar Saeed, Mahad Ali +2
Federated learning (FL) is a distributed learning technique that trains a shared model over distributed data in a privacy-preserving manner. Unfortunately, FL's performance degrade…
MAC Rate Adaptation and Cross Layer Behavior for Vehicular WiFi Access: An Experimental Study
Zafar Ayyub Qazi, Saad Nadeem, Zartash Afzal Uzmi
Vehicular WiFi is different from conventional WiFi access. Firstly, as the connections arise opportunistically, they are short lived and intermittent. Secondly, at vehicular speeds…
A Framework to Quantify the Benefits of Network Functions Virtualization in Cellular Networks
Zafar Ayyub Qazi, Vyas Sekar, Samir Das
Network functions virtualization (NFV) is an appealing vision that promises to dramatically reduce capital and operating expenses for cellular providers. However, existing efforts…