Swagath Venkataramani

Principal Researcher, AI Architecture and Compilers, International Business Machines

Joined

May 2021

Names

Swagath Venkataramani (Preferred)

Emails

****@ibm.com (Confirmed)

****@gmail.com (Confirmed)

Personal Links

Google Scholar

DBLP

Semantic Scholar

Career & Education History

Principal Researcher

AI Architecture and Compilers , International Business Machines (ibm.com)

2016 – Present

PhD student

Electrical and Computer Engineering , Purdue University (purdue.edu)

2010 – 2016

Advisors, Relations & Conflicts

PhD Advisor

Anand Raghunathan

Present

Expertise

No areas of expertise listed

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
Is Finer Better? The Limits of Microscaling Formats in Large Language Models
Andrea Fasoli, Monodeep Kar, Chi-Chun Liu, Swagath Venkataramani, Viji Srinivasan, Leland Chang, Naigang Wang
- ICLR 2026 Poster
- Readers: Everyone
SINAI: Selective Injection of Noise for Adversarial Robustness with Improved Efficiency
Zhenyu Liu, Garrett Gagnon, Swagath Venkataramani, Liu Liu
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Non-uniform Noise Injection For Enhancing DNN Adversarial Robustness And Efficiency
Zhenyu Liu, Garrett Gagnon, Swagath Venkataramani, Liu Liu
- Submitted to ICLR 2024
- Readers: Everyone
Accelerating Inference and Language Model Fusion of Recurrent Neural Network Transducers via End-to-End 4-bit Quantization
Andrea Fasoli, Chia-Yu Chen, Mauricio J. Serrano, Swagath Venkataramani, George Saon, Xiaodong Cui, Brian Kingsbury, Kailash Gopalakrishnan
- 24 Aug 2022
- OpenReview Archive Direct Upload
- 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
InterTrain: Accelerating DNN Training using Input Interpolation
Sarada Krithivasan, Swagath Venkataramani, Sanchari Sen, Anand Raghunathan
- 29 Sept 2021 (modified: 13 Feb 2023)
- ICLR 2022 Conference Withdrawn Submission
- Readers: Everyone
4-bit Quantization of LSTM-based Speech Recognition Models
Chia-Yu Chen, Andrea Fasoli, Mauricio J. Serrano, Xiao Sun, Naigang Wang, Swagath Venkataramani, George Saon, Xiaodong Cui, Brian Kingsbury, Wei Zhang, Zoltan Tuske, Kailash Gopalakrishnan
- 07 Jul 2021 (modified: 07 Jul 2021)
- OpenReview Archive Direct Upload
- Readers: Everyone
ScaleCom: Scalable Sparsified Gradient Compression for Communication-Efficient Distributed Training
Chia-Yu Chen, Jiamin Ni, Songtao Lu, Xiaodong Cui, Pin-Yu Chen, Xiao Sun, Naigang Wang, Swagath Venkataramani, Viji Srinivasan, Wei Zhang, Kailash Gopalakrishnan
- 07 Jul 2021
- OpenReview Archive Direct Upload
- Readers: Everyone

Co-Authors

View all 27 co-authors