Product
Help
Pricing
About
Jobs
Log in
Get started
Author
Add to collection
Virginia Smith
Observed name:
Smith, Virginia
Institution:
Carnegie Mellon University
Observed institution:
Carnegie Mellon University
OpenAlex ID:
A5137147658
Federated LoRA with Sparse Communication
2024
·
Kuo, Kevin
, Raje, Arian
, et al.
·
arXiv (Cornell University)
·
4
PDF
Pick Your Poison: Learning to Select Poison Sets for Stronger LLM Backdoor Attacks
2026
·
Muhamed, Aashiq
, Diab, Mona T.
, et al.
·
arXiv (Cornell University)
PDF
Decoy Direction Optimization: A Post-Hoc Defense Against LLM Abliteration
2026
·
Muhamed, Aashiq
, Diab, Mona T.
, et al.
·
arXiv (Cornell University)
PDF
Hidden in Plain Sight: Benchmarking Agent Safety Against Decomposition Attacks with DECOMPBENCH
2026
·
Kothamasu, Vikhyath
, Smith, Virginia
, et al.
·
arXiv (Cornell University)
PDF
Position: Preventing AI-Generated CSAM Necessitates New Approaches to AI Safety
2026
·
Kale, Neil
, Portnoff, Rebecca
, et al.
·
arXiv (Cornell University)
PDF
Curriculum Learning for Safety Alignment
2026
·
Kumar, Sandeep
, Smith, Virginia
, et al.
·
arXiv (Cornell University)
PDF
Pando: Do Interpretability Methods Work When Models Won't Explain Themselves?
2026
·
Zhong, Ziqian
, Muhamed, Aashiq
, et al.
·
arXiv (Cornell University)
PDF
DSPA: Dynamic SAE Steering for Data-Efficient Preference Alignment
2026
·
James Wedgwood
, Aashiq Muhamed
, et al.
·
Conference on Empirical Methods in Natural Language Processing (EMNLP)
PDF
Show more works
View as search
Works count:
8
Citation count:
4
H-index:
1
I10-index:
Year
Topic
Type
