Aounon Kumar
Scholar

Aounon Kumar

Google Scholar ID: NjhpUykAAAAJ
Research Associate, Harvard University
Machine Learning RobustnessLanguage ModelsTrustworthy ML
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
1,621
 
H-index
15
 
i10-index
15
 
Publications
20
 
Co-authors
28
list available
Contact
No contact links provided.
Publications
6 items
Search-GRT: Guided Retrieval Training of Search Agents to Optimize for Complex Question Answering
2026
Cited
0
PROGRESS: Coverage-guided RL to Train Search-augmented LLM Agent
2026
Cited
0
Detecting LLM-Written Peer Reviews
2025
Cited
0
Generalizing Trust: Weak-to-Strong Trustworthiness in Language Models
2024
Cited
0
Certifying LLM Safety against Adversarial Prompting
arXiv.org · 2023
Cited
124
Can AI-Generated Text be Reliably Detected?
arXiv.org · 2023
Cited
308
Resume (English only)
Co-authors
28 total
Soheil Feizi
Soheil Feizi
University of Maryland, College Park
Wenxiao Wang
Wenxiao Wang
RELAI.ai
Vinu Sankar Sadasivan
Vinu Sankar Sadasivan
PhD Candidate at University of Maryland, College Park
Himabindu Lakkaraju
Himabindu Lakkaraju
Assistant Professor, Harvard University; Senior Staff Research Scientist, Google.
Sriram Balasubramanian
Sriram Balasubramanian
PhD student, University of Maryland College Park
Chirag Agarwal
Chirag Agarwal
Assistant Professor, UVA
Tom Goldstein
Tom Goldstein
Volpi-Cupal Professor of Computer Science, University of Maryland
Alexander Levine
Alexander Levine
Postdoctoral Fellow, The University of Texas at Austin