Scholar
Akshat Ramachandran
Google Scholar ID: FiNleXIAAAAJ
Georgia Institute of Technology
Citations & Impact
Citations
65
H-index
4
i10-index
3
Publications
15
Co-authors
4
list available
Publications
Resume (English only)
Academic Achievements
- Paper 'MicroScopiQ: Accelerating Foundational Models through Outlier-Aware Microscaling Quantization' accepted to ISCA 2025
- Paper 'AIRCHITECT v2: Learning the Hardware Accelerator Design Space through Unified Representations' accepted to DATE 2025
- Paper 'CLAMP-ViT: Contrastive Data-Free Learning for Adaptive Post-Training Quantization of ViTs' accepted to ECCV 2024
- Presented work on 'Algorithm-Hardware Co-Design of Distribution-Aware Logarithmic-Posit Encodings for Efficient DNN Inference' at DAC 2024
- Selected as DAC Young Fellow in 2024
- Received 2nd place in ACM Student Research Competition at MICRO 2024 for MicroScopiQ
- Published in top-tier venues including DAC'24, ECCV'24, ISCA'25, DATE'25, DSD'22, ICIP'23, ICONAT'22, All Earth'23, SPIN'23
- Delivered talks at DATE 2025, ESWML Workshop (co-located with ASPLOS 2025), IBM Research, NVIDIA, and Lemurian Labs
Background
- 2nd-year Ph.D. student in Electrical and Computer Engineering (ECE) at Georgia Institute of Technology (Georgia Tech)
- Member of the Synergy Lab, advised by Prof. Tushar Krishna
- Research focuses on designing efficient and high-performance algorithms, architectures, and systems for accelerating emerging deep learning applications (computer vision and NLP)
- Adopts an interdisciplinary approach spanning the entire computing stack and breaking down traditional barriers between computing elements
- Research interests lie at the intersection of computer architecture, VLSI, computer arithmetic, and deep learning
