Souvik Kundu

Souvik Kundu

University of Southern California

H-index: 13

North America-United States

About Souvik Kundu

Souvik Kundu, With an exceptional h-index of 13 and a recent h-index of 13 (since 2020), a distinguished researcher at University of Southern California, specializes in the field of Efficient AI, Foundation models, Machine learning, Trustworthy Machine Learning, Low power design.

His recent articles reflect a diverse array of research interests and contributions to the field:

Linearizing Models for Efficient yet Robust Private Inference

Fusing Models with Complementary Expertise

Sensi-BERT: Towards Sensitivity Driven Fine-Tuning for Parameter-Efficient Language Model

Analyzing Adversarial Vulnerabilities of Graph Lottery Tickets

AFLoRA: Adaptive Freezing of Low Rank Adaptation in Parameter Efficient Fine-Tuning of Large Models

GEAR: An efficient KV cache compression recipefor near-lossless generative inference of llm

ViTA: A Vision Transformer Inference Accelerator for Edge Applications

RNA-ViT: Reduced-Dimension Approximate Normalized Attention Vision Transformers for Latency Efficient Private Inference

Souvik Kundu Information

University

Position

Ph.D. candidate

Citations(all)

590

Citations(since 2020)

589

Cited By

35

hIndex(all)

13

hIndex(since 2020)

13

i10Index(all)

19

i10Index(since 2020)

19

Email

University Profile Page

University of Southern California

Google Scholar

View Google Scholar Profile

Souvik Kundu Skills & Research Interests

Efficient AI

Foundation models

Machine learning

Trustworthy Machine Learning

Low power design

Top articles of Souvik Kundu

Title

Journal

Author(s)

Publication Date

Linearizing Models for Efficient yet Robust Private Inference

arXiv preprint arXiv:2402.05521

Sreetama Sarkar

Souvik Kundu

Peter A Beerel

2024/2/8

Fusing Models with Complementary Expertise

arXiv preprint arXiv:2310.01542

Hongyi Wang

Felipe Maia Polo

Yuekai Sun

Souvik Kundu

Eric Xing

...

2023/10/2

Sensi-BERT: Towards Sensitivity Driven Fine-Tuning for Parameter-Efficient Language Model

Souvik Kundu

Sharath Nittur Sridhar

Maciej Szankin

Sairam Sundaresan

2024/4/14

Analyzing Adversarial Vulnerabilities of Graph Lottery Tickets

Subhajit Dutta Chowdhury

Zhiyu Ni

Qingyuan Peng

Souvik Kundu

Pierluigi Nuzzo

2024/4/14

AFLoRA: Adaptive Freezing of Low Rank Adaptation in Parameter Efficient Fine-Tuning of Large Models

arXiv preprint arXiv:2403.13269

Zeyu Liu

Souvik Kundu

Anni Li

Junrui Wan

Lianghao Jiang

...

2024/3/20

GEAR: An efficient KV cache compression recipefor near-lossless generative inference of llm

arXiv preprint arXiv:2403.05527

Hao Kang

Qingru Zhang

Souvik Kundu

Geonhwa Jeong

Zaoxing Liu

...

2024/3/8

ViTA: A Vision Transformer Inference Accelerator for Edge Applications

Shashank Nag

Gourav Datta

Souvik Kundu

Nitin Chandrachoodan

Peter A Beerel

2023/5/21

RNA-ViT: Reduced-Dimension Approximate Normalized Attention Vision Transformers for Latency Efficient Private Inference

Dake Chen

Yuke Zhang

Souvik Kundu

Chenghao Li

Peter A Beerel

2023/10/28

NeRFool: Uncovering the Vulnerability of Generalizable Neural Radiance Fields against Adversarial Perturbations

International Conference on Machine Learning (ICML) 2023

Yonggan Fu

Ye Yuan

Souvik Kundu

Shang Wu

Shunyao Zhang

...

2023/7

Sparse Mixture Once-for-all Adversarial Training for Efficient in-situ Trade-off between Accuracy and Robustness of DNNs

Souvik Kundu

Sairam Sundaresan

Sharath Nittur Sridhar

Shunlin Lu

Han Tang

...

2023/6/4

FireFly A Synthetic Dataset for Ember Detection in Wildfire

Yue Hu

Xinan Ye

Yifei Liu

Souvik Kundu

Gourav Datta

...

2023

Making Models Shallow Again: Jointly Learning to Reduce Non-Linearity and Depth for Latency-Efficient Private Inference

Souvik Kundu

Yuke Zhang

Dake Chen

Peter A Beerel

2023

Development of a small cell lung cancer organoid model to study cellular interactions and survival after chemotherapy

Frontiers in Pharmacology

Chandani Sen

Caroline Koloff

Souvik Kundu

Dan C Wilkinson

Juliette Yang

...

2023/8/7

Revisiting Sparsity Hunting in Federated Learning: Why does Sparsity Consensus Matter?

Transactions on Machine Learning Research

Sara Babakniya

Souvik Kundu

Saurav Prakash

Yue Niu

Salman Avestimehr

2023/7/20

Sparse but Strong: Crafting Adversarially Robust Graph Lottery Tickets

arXiv preprint arXiv:2312.06568

Subhajit Dutta Chowdhury

Zhiyu Ni

Qingyuan Peng

Souvik Kundu

Pierluigi Nuzzo

2023/12/11

C2PI: An Efficient Crypto-Clear Two-Party Neural Network Private Inference

Yuke Zhang

Dake Chen

Souvik Kundu

Haomei Liu

Ruiheng Peng

...

2023/7/9

SAL-ViT: Towards Latency Efficient Private Inference on ViT using Selective Attention Search with a Learnable Softmax Approximation

Yuke Zhang

Dake Chen

Souvik Kundu

Chenghao Li

Peter A Beerel

2023

Recent Advances in Scalable Energy-Efficient and Trustworthy Spiking Neural networks: from Algorithms to Technology

Souvik Kundu

Rui-Jie Zhu

Akhilesh Jaiswal

Peter A Beerel

2024/4/14

Overcoming Resource Constraints in Federated Learning: Large Models Can Be Trained with only Weak Clients

Transactions on Machine Learning Research

Yue Niu*

Saurav Prakash*

Souvik Kundu

Sunwoo Lee

Salman Avestimehr (* = equal contribution)

2023/10

Learning to Linearize Deep Neural Networks for Secure and Efficient Private Inference

arXiv preprint arXiv:2301.09254

Souvik Kundu

Shunlin Lu

Yuke Zhang

Jacqueline Liu

Peter A Beerel

2023/1/23

See List of Professors in Souvik Kundu University(University of Southern California)

Co-Authors

H-index: 114
Eric Xing

Eric Xing

Carnegie Mellon University

H-index: 59
Salman Avestimehr

Salman Avestimehr

University of Southern California

H-index: 39
Peter Beerel

Peter Beerel

University of Southern California

H-index: 24
Yuekai Sun

Yuekai Sun

University of Michigan

H-index: 14
Hongyi Wang

Hongyi Wang

University of Wisconsin-Madison

academic-engine