Zaid Khan
3 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
This paper demonstrates that Large Language Models (LLMs) can serve as accurate and selective surrogates for costly GPU kernel performance measurements, significantly expanding the search space for optimizing deep learning kernels.
This paper demonstrates that Large Language Models (LLMs) can serve as accurate and selective surrogates for costly GPU kernel performance measurements, significantly expanding the search space for optimizing deep learning kernels.
The authors introduce HiViG, a test-time framework for improving the performance of Computer Use Agents in GUI environments.
Papers
A History-Aware Visually Grounded Critic for Computer Use Agents
Jaewoo Lee, Zaid Khan, Archiki Prasad, Justin Chih-Yao Chen +6 more
The authors introduce HiViG, a test-time framework for improving the performance of Computer Use Agents in GUI environments.