Tejaswini Pedapati

Joined

July 2019

Names

Tejaswini Pedapati

Emails

****@us.ibm.com (Confirmed)

Personal Links

Google Scholar

DBLP

ACL Anthology

Career & Education History

Research Engineer

International Business Machines (ibm.com)

2014 – 2025

MS student

Computer Science, Columbia University (columbia.edu)

2012 – 2013

Advisors, Relations & Conflicts

Coauthor

Martin Wistuba

2018 – 2022

Expertise

Model compression

2024 – 2025

Efficient Fine-tuning

2024 – 2025

Neural Architecture Search

2017 – 2023

Publications

EpMAN: Episodic Memory AttentioN for Generalizing to Longer Contexts
Subhajit Chaudhury, Payel Das, Sarathkrishna Swaminathan, Georgios Kollias, Elliot Nelson, Khushbu Pahwa, Tejaswini Pedapati, Igor Melnyk, Matthew Riemer
- ACL
- Readers: Everyone
ADAPT: Adaptive Prompt Tuning for Vision-Language Models
Zhenhan Huang, Tejaswini Pedapati, Pin-Yu Chen, Jianxi Gao
- Accepted by TMLR
- Readers: Everyone
CoFrGeNet: Continued Fraction Architectures for Language Generation
Amit Dhurandhar, Vijil Chenthamarakshan, Dennis Wei, Tejaswini Pedapati, Karthikeyan Natesan Ramamurthy, Rahul Nair
- Submitted to ICLR 2026
- Readers: Everyone
OjaKV: Context-Aware Online Low-Rank KV Cache Compression with Oja’s Rule
Yuxuan Zhu, David H. Yang, Mohammad Mohammadi Amiri, Keerthiram Murugesan, Tejaswini Pedapati, Pin-Yu Chen
- ICLR 2026 Conference Withdrawn Submission
- Readers: Everyone
Intermediate Representations are Strong Training-Free AI-Generated Image Detectors
Zhenhan Huang, Pin-Yu Chen, Tejaswini Pedapati, Jianxi Gao
- Submitted to ICLR 2026
- Readers: Everyone
Large Language Model Confidence Estimation via Black-Box Access
Tejaswini Pedapati, Amit Dhurandhar, Soumya Ghosh, Soham Dan, Prasanna Sattigeri
- Accepted by TMLR
- Readers: Everyone
Sparse Gradient Compression for Fine-Tuning Large Language Models
David H. Yang, Mohammad Mohammadi Amiri, Tejaswini Pedapati, Subhajit Chaudhury, Pin-Yu Chen
- SLLM
- Readers: Everyone
Granite Guardian
Inkit Padhi, Manish Nagireddy, Giandomenico Cornacchia, Subhajit Chaudhury, Tejaswini Pedapati, Pierre Dognin, Keerthiram Murugesan, Erik Miehling, Martín Santillán Cooper, Kieran Fraser, Giulio Zizzo, Muhammad Zaid Hameed, Mark Purcell, Michael Desmond, Qian Pan, Zahra Ashktorab, Inge Vejsbjerg, Elizabeth M. Daly, Michael Hind, Werner Geyer et al. (3 additional authors not shown)
- OpenReview Archive Direct Upload
- Readers: Everyone
Differentiable Prompt Learning for Vision Language Models
Zhenhan Huang, Tejaswini Pedapati, Pin-Yu Chen, Jianxi Gao
- CoRR 2025
- Readers: Everyone
Model Agnostic Contrastive Explanations for Classification Models
Amit Dhurandhar, Tejaswini Pedapati, Avinash Balakrishnan, Pin-Yu Chen, Karthikeyan Shanmugam, Ruchir Puri
- IEEE J. Emerg. Sel. Topics Circuits Syst. 2024
- Readers: Everyone

View all 43 publications

Co-Authors

View all 102 co-authors