Emad Haque

Papers

Total Citations

H-Index

About

Emad Haque is a leading researcher at the forefront of AI hardware architecture, with a primary focus on designing scalable, efficient systems for next-generation machine learning. His most cited work, "CLAIRE: Composable Chiplet Libraries for AI Inference" (2025, 4 citations), addresses a critical bottleneck in modern AI: the immense computational demands of models like GPT-4 and LLaMAv3, which push monolithic chips to their technological limits. Haque’s major contribution lies in pioneering chiplet-based design libraries that enable composable, modular hardware—allowing AI accelerators to be assembled from smaller, reusable dies rather than single, monolithic processors. This approach promises to slash costs, improve yield, and dramatically scale inference performance. While his citation count is still growing, the foundational nature of this work positions him as a key architect in the shift toward disaggregated computing for AI. His research directly impacts fields from computer vision to healthcare robotics, offering a practical path to meeting the insatiable compute needs of tomorrow’s models. For students and researchers, Haque’s work represents a vital bridge between hardware innovation and real-world AI deployment.