4 papers · 1 filter
Double-Take: Improving Capacity, Binding, and Selectivity In Long-Context Within Bidirectional Memory
Vakul Raghavan, Utkarsh Grover, Mingyang Mao +2
Processing a long sequence does not guarantee that distant information remains usable. As context grows, a fixed-size memory must retain many associations, connect information acro…
ORACLE: Optimizer-Relative Alignment for Constrained LEarning
Utkarsh Grover, Wyatt Mackey, Kaixun Hua +2
Constraint handling methods typically intervene before the optimizer acts, by modifying the objective or the gradient. Yet momentum, adaptive scaling, and structured preconditionin…
DePICT: Decision-Preserving Interface for Constrained Downstream Tasks
Utkarsh Grover, Ravi Ranjan, Agoritsa Polyzou +5
A constrained optimization problem may involve a parameter in its objective and active constraints, yet the final decision may remain insensitive to small changes in that parameter…
G-Drift MIA: Membership Inference via Gradient-Induced Feature Drift in LLMs
Ravi Ranjan, Utkarsh Grover, Xiaomin Lin +1
Large language models (LLMs) are trained on massive web-scale corpora, raising growing concerns about privacy and copyright. Membership inference attacks (MIAs) aim to determine wh…