Keerthiram Murugesan

Researcher, Research, International Business Machines

Joined

October 2017

Names

Emails

****@cs.cmu.edu (Confirmed)

****@gmail.com (Confirmed)

****@ibm.com (Confirmed)

Personal Links

Career & Education History

Researcher

Research, International Business Machines (ibm.com)

2018 – Present

PhD student

Language Technologies and Machine Learning, Carnegie Mellon University (cmu.edu)

2012 – 2018

MS student

Computer Science, University of Kentucky (uky.edu)

2008 – 2011

Advisors, Relations & Conflicts

PhD Advisor

Dr. Jaime Carbonell

2012 – 2018

Expertise

Generative AI

Large Language Models

Trustworthy AI

Multitask learning

Reinforcement learning

2012 – Present

Publications

Patching LLMs Like Software: A Lightweight Method for Improving Safety Policies in Large Language Models
Huzaifa Arif, Pin-Yu Chen, Keerthiram Murugesan, Alex Gittens, Payel Das, Ching-Yun Ko
- ICLR 2026 Trustworthy AI
- Readers: Everyone
Context Attribution with Multi-Armed Bandit Optimization
DENG PAN, Keerthiram Murugesan, Nuno Moniz, Nitesh V Chawla
- ICLR 2026 Conference Withdrawn Submission
- Readers: Everyone
Patching LLM like Software: A Lightweight Method for improving existing policy in Large Language Models
Huzaifa Arif, Keerthiram Murugesan, Ching-Yun Ko, Pin-Yu Chen, Payel Das, Alex Gittens
- Submitted to ICLR 2026
- Readers: Everyone
EfficientLLM: Evaluating Large Language Models Efficiency
Zhengqing Yuan, Weixiang Sun, Yixin Liu, Huichi Zhou, Rong Zhou, Yiyang Li, Zheyuan Zhang, Wei Song, Yue Huang, Haolong Jia, Keerthiram Murugesan, Yu Wang, Lifang He, Jianfeng Gao, Lichao Sun, Yanfang Ye
- ICLR 2026 Conference Desk Rejected Submission
- 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- ICLR 2026 Conference Withdrawn Submission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
AutoData: A Multi-Agent System for Open Web Data Collection
Tianyi Ma, Yiyue Qian, Zheyuan Zhang, Zehong Wang, Xiaoye Qian, Feifan Bai, Yifan Ding, Xuwei Luo, Shinan Zhang, Keerthiram Murugesan, Chuxu Zhang, Yanfang Ye
- NeurIPS 2025 poster
- Readers: Everyone
The Unlearning Mirage: A Dynamic Framework for Evaluating LLM Unlearning
Raj Sanjay Shah, Jing Huang, Keerthiram Murugesan, Nathalie Baracaldo, Diyi Yang
- COLM 2025
- 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
Combinatorial Multi-armed Bandits: Arm Selection via Group Testing
Arpan Mukherjee, Shashanka Ubaru, Keerthiram Murugesan, Karthikeyan Shanmugam, Ali Tajer
- Accepted by TMLR
- Readers: Everyone
Group Fair Federated Learning via Stochastic Kernel Regularization
Huzaifa Arif, Pin-Yu Chen, Keerthiram Murugesan, Alex Gittens
- Accepted by TMLR
- Readers: Everyone

View all 33 publications

Co-Authors

View all 116 co-authors