Zafaryab Haider
Papers
1
Total Citations
2
H-Index
1
About
Zafaryab Haider is a rising researcher at the forefront of efficient artificial intelligence, with a primary focus on neural architecture search (NAS) and multi-task learning. His most notable contribution is the development of **Intelligent Layer Sharing (ILASH)**, a predictive framework that automates the design of compact neural networks for resource-constrained, multi-task applications—such as those found in healthcare, autonomous vehicles, and robotics. By intelligently identifying which layers can be shared across tasks, ILASH dramatically reduces computational overhead without sacrificing accuracy, addressing a critical bottleneck in deploying AI on edge devices. Though early in his career, his 2025 paper on ILASH has already garnered 2 citations, signaling growing interest in his work. Haider’s research stands out for its practical focus: rather than merely optimizing for performance, he prioritizes real-world deployability, making his contributions particularly valuable for embedded systems and real-time analytics. As the demand for efficient, multi-tasking AI accelerates, Haider’s innovations position him as a key architect of next-generation, resource-aware neural networks.
Research Focus
Key Achievements
Top Papers
- 1