ConferenceOralKDD2026
TamperBench: Systematically Stress-Testing LLM Safety Under Fine-Tuning and Tampering
Saad Hossain, Tom Tseng, Punya Syon Pandey, Samanvay Vajpayee, Matthew Kowal, Nayeema Nonta, Samuel Simko, Stephen Casper, Zhijing Jin, Kellin Pelrine, Sirisha Rambhatla
ConferenceNeurIPS2025
SubTrack++: Gradient Subspace Tracking for Scalable LLM Training
Sahar Rajabi, Nayeema Nonta, Sirisha Rambhatla
WorkshopICLR Workshop on Test-Time Updates2026
Refusal-Orthogonal Gated Editing for Safer Localized LLM Adaptation
Nayeema Nonta, Sirisha Rambhatla
WorkshopICLR Workshop on Representational Alignment2026
Safe Downstream Adaptation of LLMs via Refusal-Orthogonal Gated Editing
Nayeema Nonta, Sirisha Rambhatla
WorkshopICLR Workshops2026
TamperBench: A Systematic Framework to Stress-Test LLM Safety Under Fine-Tuning and Tampering
Saad Hossain, Tom Tseng, Punya Syon Pandey, Samanvay Vajpayee, Matthew Kowal, Nayeema Nonta, Samuel Simko, Stephen Casper, Zhijing Jin, Kellin Pelrine, Sirisha Rambhatla
WorkshopICLR Workshop on Geometry-grounded Representation Learning and Generative Modeling2026
Random but Right: A Geometric Explanation for Efficient LLM Training
Sahar Rajabi, Nayeema Nonta, Sirisha Rambhatla
WorkshopICLR Workshop on Deep Generative Model in Machine Learning2026
Principled Randomized Exploration of Gradient Subspaces for Efficient LLM Training
Sahar Rajabi, Nayeema Nonta, Sirisha Rambhatla