Pedro Gimenes

I am a PhD student in Deep Learning Systems at Imperial College London. My work blends hardware, systems and algorithms in topics spanning agentic reasoning, adaptive inference serving systems and Machine Learning compilers. My CV is available here.

I am a regular committer in open-source projects such as Mase.
I enjoy weightlifting and Muay Thai.
I occasionally read books and write about them here.

Recent Work

• ARIES: Autonomous Reasoning with LLMs on Interactive Thought Graph Environments
  Pedro Gimenes, Zeyu Cao, Jeffrey Wong, Yiren Zhao
  February 2025
  pre-print

• AMPLE: Event-Driven Accelerator for Mixed-Precision Inference of Graph Neural Networks
  Pedro Gimenes, Yiren Zhao, George Constantinides
  EuroMLSys ‘25, March 30 - April 3, 2025, Rotterdam, Netherlands
  pre-print

• LLM4DV: Using Large Language Models for Hardware Test Stimuli Generation
  Zixi Zhang, Balint Szekely, Pedro Gimenes, Greg Chadwick, Hugo McNally, Jianyi Cheng, Robert Mullins, Yiren Zhao
  FCCM ‘25, May 4 - May 7, 2024, Fayetteville, Arkansas, USA
  pre-print

• Scaling Laws for Mixed Quantization in Large Language Models
  Zeyu Cao, Cheng Zhang, Pedro Gimenes, Jianqiao Lu, Jianyi Cheng, Yiren Zhao
  October 2024
  pre-print

See Publications for a complete list.