Vimal William

prof_pic.jpg

Vimal (விமல்) is a PhD student at the University of Arizona, USA, jointly advised by Prof. Huanrui Yang and Prof. Danella Zhao. Prior to this, he worked as a Systems Software Engineer in Edge AI and hardware at SandLogic Technologies, India.

Research Interest

He is working on improving AI inference efficiency through algorithmic and compiler optimizations, as well as the design of efficient hardware architectures. His prior work has focused on neural network compression via pruning algorithms, approximate and fixed-point computation for non-linear operations, and the development of end-to-end low-precision quantization pipelines.

"A computer would deserve to be called intelligent if it could deceive a human into believing that it was human." - Alan Turing

news

Mar 31, 2026 Selected as a DAC Young Fellow at the DAC Conference 2026.
Aug 01, 2025 Started Ph.D. in Electrical and Computer Engineering (ECE) as a Herbold Fellow.
Jun 01, 2023 Joined SandLogic Technologies as a System Software Engineer
Feb 01, 2023 Graduated with a B.E. in Electronics and Communication Engineering from Anna University with First Class with Distinction.

selected publications

  1. arXiv
    GLIDE: Guided Layerwise Hybrid Attention for Efficient LLM Inference
    Vimal William, Ravi Tandon, and Jyotikrishna Dass
    2026
  2. VDAT
    TYTAN: Taylor-series based Non-Linear Activation Engine for Deep Learning Accelerators
    Soham Pramanik*, Vimal William*, Arnab Raha, and 3 more authors
    2025
  3. arXiv
    Deep Learning Architecture for Motor Imaged Words
    Vimal W* and Akshansh Gupta
    2023