Sourjya Roy

According to our database, Sourjya Roy authored at least 13 papers between 2016 and 2026.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2026

Softprox: A Post-Finetuning Methodology to Mitigate Softmax Bottlenecks in Transformer Workloads.

Aradhana Mohan Parvathy, Sourjya Roy, Soumendu Kumar Ghosh, Arnab Raha, Deepak Mathaikutty, Anand Raghunathan

IEEE Trans. Circuits Syst. Artif. Intell., April, 2026

2025

KV-CAR: KV Cache Compression using Autoencoders and KV Reuse in Large Language Models.

Sourjya Roy, Shrihari Sridharan, Surya Selvam, Anand Raghunathan

CoRR, December, 2025

Experts are all you need: A Composable Framework for Large Language Model Inference.

Shrihari Sridharan, Sourjya Roy, Anand Raghunathan, Kaushik Roy

CoRR, November, 2025

2023

Evaluation of STT-MRAM as a Scratchpad for Training in ML Accelerators.

Sourjya Roy, Cheng Wang, Anand Raghunathan

CoRR, 2023

2022

Compute-in-Memory Technologies and Architectures for Deep Learning Workloads.

Mustafa Fayez Ali, Sourjya Roy, Utkarsh Saxena, Tanvi Sharma, Anand Raghunathan, Kaushik Roy

IEEE Trans. Very Large Scale Integr. Syst., 2022

2021

TxSim: Modeling Training of Deep Neural Networks on Resistive Crossbar Systems.

Sourjya Roy, Shrihari Sridharan, Shubham Jain, Anand Raghunathan

IEEE Trans. Very Large Scale Integr. Syst., 2021

PIM-DRAM: Accelerating Machine Learning Workloads Using Processing in Commodity DRAM.

Sourjya Roy, Mustafa Fayez Ali, Anand Raghunathan

IEEE J. Emerg. Sel. Topics Circuits Syst., 2021

Design Tools for Resistive Crossbar based Machine Learning Accelerators.

Indranil Chakraborty, Sourjya Roy, Shrihari Sridharan, Mustafa Fayez Ali, Aayush Ankit, Shubham Jain, Anand Raghunathan

Proceedings of the 3rd IEEE International Conference on Artificial Intelligence Circuits and Systems, 2021

2020

Resistive Crossbars as Approximate Hardware Building Blocks for Machine Learning: Opportunities and Challenges.

Indranil Chakraborty, Mustafa Fayez Ali, Aayush Ankit, Shubham Jain, Sourjya Roy, Shrihari Sridharan, Amogh Agrawal, Anand Raghunathan, Kaushik Roy

Proc. IEEE, 2020

Gradual Channel Pruning While Training Using Feature Relevance Scores for Convolutional Neural Networks.

Sai Aparna Aketi, Sourjya Roy, Anand Raghunathan, Kaushik Roy

IEEE Access, 2020

Pruning Filters while Training for Efficiently Optimizing Deep Learning Networks.

Sourjya Roy, Priyadarshini Panda, Gopalakrishnan Srinivasan, Anand Raghunathan

Proceedings of the 2020 International Joint Conference on Neural Networks, 2020

2017

Spike timing dependent plasticity based enhanced self-learning for efficient pattern recognition in spiking neural networks.

Gopalakrishnan Srinivasan, Sourjya Roy, Vijay Raghunathan, Kaushik Roy

Proceedings of the 2017 International Joint Conference on Neural Networks, 2017

2016

Proposal for a Leaky-Integrate-Fire Spiking Neuron based on Magneto-Electric Switching of Ferro-magnets.

Akhilesh Jaiswal, Sourjya Roy, Gopalakrishnan Srinivasan, Kaushik Roy

CoRR, 2016