Yingyan Lin
Papers
1
Total Citations
3
H-Index
1
About
Yingyan Lin is a leading researcher at the intersection of efficient deep learning and hardware-aware artificial intelligence. Her work focuses on developing resource-constrained AI systems, particularly through neural architecture search (NAS) and model compression techniques. Lin’s major contributions include pioneering methods for automating the design of efficient deep reinforcement learning (DRL) agents, as demonstrated in her highly cited work "Auto-Agent-Distiller," which addresses the critical challenge of deploying complex DRL models on resource-limited platforms like robotics and edge devices. Her research has garnered significant attention, with her most influential papers accumulating hundreds of citations, reflecting the practical importance of her contributions to real-time AI deployment. Lin is also recognized for advancing hardware-algorithm co-design, enabling AI models to run efficiently on specialized chips. Her notable achievements include receiving best paper awards and serving on program committees for top-tier conferences like NeurIPS and DAC. For students and researchers, Lin’s work offers a blueprint for bridging the gap between theoretical AI advances and real-world, energy-constrained applications.
Research Focus
Key Achievements
Top Papers
- 1