Keerthiram Murugesan
Scholar

Keerthiram Murugesan

Google Scholar ID: -698GEMAAAAJ
Research Scientist, IBM Research AI/ Carnegie Mellon University
Machine learningArtificial Intelligence
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
992
 
H-index
16
 
i10-index
24
 
Publications
20
 
Co-authors
0
 
Contact
Emailkeerthiram.murugesan@ibm.comTwitterOpen ↗GitHubOpen ↗LinkedInOpen ↗
Publications
16 items
Activation-Conditioned Self-Distillation
2026
Cited
0
Mitigating Misalignment Contagion by Steering with Implicit Traits
2026
Cited
0
ZoomR: Memory Efficient Reasoning through Multi-Granularity Key Value Retrieval
2026
Cited
0
The Unlearning Mirage: A Dynamic Framework for Evaluating LLM Unlearning
2026
Cited
0
AgentSCOPE: Evaluating Contextual Privacy Across Agentic Workflows
2026
Cited
0
Food4All: A Multi-Agent Framework for Real-time Free Food Discovery with Integrated Nutritional Metadata
2025
Cited
0
Interpretable Graph-Language Modeling for Detecting Youth Illicit Drug Use
2025
Cited
0
NG-Router: Graph-Supervised Multi-Agent Collaboration for Nutrition Question Answering
2025
Cited
0
Resume
Academic Achievements
  • Published 'Text-based RL Agents with Commonsense Knowledge: New Challenges, Environments and Baselines' at AAAI 2021.
  • Co-authored 'Thinking Fast and Slow in AI' presented at AAAI 2021.
  • Published 'Plansformer: Generating Symbolic Plans using Transformers' as arXiv preprint arXiv:2212.08681 in 2022.
  • Published 'STARLING: Self-supervised Training of Text-based Reinforcement Learning Agent with Large Language Models' in ACL 2024 Findings.
  • Contributed to 'Granite Guardian: Comprehensive LLM Safeguarding' accepted at NAACL 2025 Industry Track.