Sanchari Sen

Researcher, International Business Machines

Joined

September 2019

Names

Sanchari Sen (Preferred)

Emails

****@purdue.edu (Confirmed)

****@ibm.com (Confirmed)

Personal Links

Google Scholar

Career & Education History

Researcher

International Business Machines (ibm.com)

2020 – Present

PhD student

Purdue University (purdue.edu)

2015 – 2020

Advisors, Relations & Conflicts

Coauthor

Shubham Jain

2018 – Present

Coauthor

Swagath Venkataramani

2017 – Present

PhD Advisor

Anand Raghunathan

2015 – Present

Expertise

Deep Learning

RNNs

CNNs

SNNs

Neuromorphic computing

Hardware accelerators

Present

Publications

SINAI: Strategic Injection of Noise for Adversarial Defense with Improved Accuracy–Robustness Tradeoffs
Zhenyu Liu, Yayue Hou, Sanchari Sen, Swagath Venkataramani, Nan Wu, Liu Liu
- Submitted to ICLR 2026
- Readers: Everyone
Deep Compression of Pre-trained Transformer Models
Naigang Wang, Chi-Chun Liu, Swagath Venkataramani, Sanchari Sen, Chia-Yu Chen, Kaoutar El Maghraoui, Viji Srinivasan, Leland Chang
- Published: 31 Oct 2022, Last Modified: 12 Jan 2023
- NeurIPS 2022 Accept
- Readers: Everyone
Specialized Transformers: Faster, Smaller and more Accurate NLP Models
Amrit Nagarajan, Sanchari Sen, Jacob R. Stevens, Anand Raghunathan
- Published: 28 Jan 2022, Last Modified: 13 Feb 2023
- ICLR 2022 Submitted
- Readers: Everyone
Accelerating DNN Training through Selective Localized Learning
Sarada Krithivasan, Sanchari Sen, Swagath Venkataramani, Anand Raghunathan
- 28 Sept 2020 (modified: 05 May 2023)
- ICLR 2021 Conference Blind Submission
- Readers: Everyone
Optimizing Transformers with Approximate Computing for Faster, Smaller and more Accurate NLP Models
Amrit Nagarajan, Sanchari Sen, Jacob R. Stevens, Anand Raghunathan
- 28 Sept 2020 (modified: 12 Oct 2025)
- ICLR 2021 Conference Blind Submission
- Readers: Everyone

Sanchari Sen

Names

Emails

Personal Links

Career & Education History

Advisors, Relations & Conflicts

Expertise

Publications

SINAI: Strategic Injection of Noise for Adversarial Defense with Improved Accuracy–Robustness Tradeoffs

Deep Compression of Pre-trained Transformer Models

Specialized Transformers: Faster, Smaller and more Accurate NLP Models

Accelerating DNN Training through Selective Localized Learning

Optimizing Transformers with Approximate Computing for Faster, Smaller and more Accurate NLP Models

Co-Authors