Martin Pawelczyk
Scholar

Martin Pawelczyk

Google Scholar ID: oYAf_hgAAAAJ
Postdoc, Harvard University
Machine LearningML SafetyTrustworthy MLLLMs
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
3,012
 
H-index
16
 
i10-index
16
 
Publications
20
 
Co-authors
25
list available
Contact
No contact links provided.
Publications
6 items
Don't Trust Stubborn Neighbors: A Security Framework for Agentic Networks
2026
Cited
0
Easy Data Unlearning Bench
2026
Cited
0
Train Once, Answer All: Many Pretraining Experiments for the Cost of One
2025
Cited
0
Efficiently Verifiable Proofs of Data Attribution
2025
Cited
0
Generalizing Trust: Weak-to-Strong Trustworthiness in Language Models
2024
Cited
0
Machine Unlearning Fails to Remove Data Poisoning Attacks
arXiv.org · 2024
Cited
6
Resume (English only)
Co-authors
25 total
Gjergji Kasneci
Gjergji Kasneci
Professor at the Technical University of Munich
Co-author 2
Co-author 2
Himabindu Lakkaraju
Himabindu Lakkaraju
Assistant Professor, Harvard University; Senior Staff Research Scientist, Google.
Co-author 4
Co-author 4
Vadim Borisov
Vadim Borisov
tabularis.ai
Kathrin Seßler
Kathrin Seßler
Technical University of Munich
Chirag Agarwal
Chirag Agarwal
Assistant Professor, UVA
Co-author 8
Co-author 8