Shubham Agarwal
Scholar

Shubham Agarwal

Google Scholar ID: jzTgdZoAAAAJ
UC Berkeley
ML for SystemsSystems for ML
Citations & Impact
All-time
Citations
90
 
H-index
5
 
i10-index
2
 
Publications
13
 
Co-authors
23
list available
Resume (English only)
Academic Achievements
  • Published papers 'Cache-Craft: Managing Chunk-Caches for Efficient Retrieval-Augmented Generation' (SIGMOD'25) and 'ReCON: Training-Free Acceleration for Text-to-Image Synthesis with Retrieval of Concept Prompt Trajectories' (ECCV’24).
Research Experience
  • Previously a Research Associate at Adobe Research, working with Dr. Subrata Mitra and Dr. Shiv Kumar Saini, building large-scale systems for generative models, optimizing efficiency and resource use, and developing ML tools for outage prediction and failure diagnosis.
Education
  • Graduated from BITS Pilani with a Bachelor's in Computer Science in 2022; currently pursuing a PhD at UC Berkeley's Sky Lab, advised by Prof. Ion Stoica and Prof. Aditya Parameswaran.
Background
  • PhD student in Computer Science, focusing on ML Systems, improving the reliability and efficiency of LLMs and agents.
Miscellany
  • Can be reached via email at shubham3@berkeley.edu.