Scholar
Shivam Aggarwal
Google Scholar ID: FTkZZTMAAAAJ
Senior AI Compiler Engineer, Renesas
Efficient AI
Model Compression
Quantization
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
118
H-index
5
i10-index
3
Publications
12
Co-authors
10
list available
Contact
Email
shivam@comp.nus.edu.sg
CV
Open ↗
Twitter
Open ↗
GitHub
Open ↗
LinkedIn
Open ↗
Publications
5 items
Efficient Text-to-Image Generation: An Adaptive Step Schedule Controller for Diffusion Models
2026
Cited
0
HALO: Hardware-aware quantization with low critical-path-delay weights for LLM acceleration
2025
Cited
0
TerEffic: Highly Efficient Ternary LLM Inference on FPGA
2025
Cited
0
DAOP: Data-Aware Offloading and Predictive Pre-Calculation for Efficient MoE Inference
arXiv.org · 2024
Cited
0
Condensed Data Expansion Using Model Inversion for Knowledge Distillation
2024
Cited
1
Resume
Academic Achievements
Post-Training Quantization with Low-precision Minifloats and Integers on FPGAs
Condensed Data-Guided Privacy-Preserving Knowledge Distillation
CRISP: Hybrid Structured Sparsity for Class-aware Model Pruning (DATE 2024)
Chameleon: Dual Memory Replay for Online Continual Learning on Edge Devices (IEEE TCAD 2024, DATE 2023)
Robust and Resource-Efficient Data-Free Knowledge Distillation by Generative Pseudo Replay (AAAI 2022)
Symmetric k-means for Deep Neural Network Compression and Hardware Acceleration on FPGAs (IEEE J-STSP, March 2020)
Synthetic Video Generation for Robust Hand Gesture Recognition in Augmented Reality Applications (HANDS Workshop @ ICCV 2019)
Co-authors
7 total
Tulika Mitra
Professor of Computer Science, National University of Singapore
Michaela Blott
AMD Research
Alessandro Pappalardo
AMD
Thomas B. Preußer
AMD Research
Saket Anand
Associate Professor, Indraprastha Institute of Information Technology
Varun Jain
The Robotics Institute, Carnegie Mellon University
Ramya Hebbalaguppe
Senior Scientist, TCS Research Labs