5 citations · 7 across the 10 of their papers we have counts for
5 papers · 1 filter
Leaky Students: Membership Inference against On-Policy Distillation
Zhexi Lu, Mingzhi Zhu, Stacy Patterson +1
On-policy distillation (OPD) trains a student to match a teacher's next-token distributions on student-generated trajectories. However, privileged information supplied to the teach…
CRANE: Constrained Reasoning Injection for Code Agents via Nullspace Editing
Mingzhi Zhu, Michele Merler, Raju Pavuluri +1
Code agents must both reason over long-horizon repository state and obey strict tool-use protocols. In paired Instruct/Thinking checkpoints, these capabilities are complementary bu…
Improving Parameter-Efficient Federated Learning with Differentially Private Refactorization
Linh Tran, Ana Milanova, Stacy Patterson
Federated Learning (FL) with parameter-efficient fine-tuning, such as Low-Rank Adaptation (LoRA), enables scalable model training on distributed data. However, when combined with D…
Measuring Privacy Risks and Tradeoffs in Financial Synthetic Data Generation
Michael Zuo, Inwon Kang, Stacy Patterson +1
We explore the privacy-utility tradeoff of synthetic data generation schemes on tabular financial datasets, a domain characterized by high regulatory risk and severe class imbalanc…
Multi-task Code LLMs: Data Mix or Model Merge?
Mingzhi Zhu, Boris Sobolev, Rahul Krishna +3
Recent research advocates deploying smaller, specialized code LLMs in agentic frameworks alongside frontier models, sparking interest in efficient strategies for multi-task learnin…