4 papers · 1 filter
ActiveDPO: Active Direct Preference Optimization for Sample-Efficient Alignment
Xiaoqiang Lin, Arun Verma, Zhongxiang Dai +3
The recent success in using human preferences to align large language models (LLMs) has significantly improved their performance in various downstream tasks, such as question answe…
Preconditioned DeltaNet: Curvature-aware Sequence Modeling for Linear Recurrences
Neehal Tumma, Noel Loo, Daniela Rus
To address the increasing long-context compute limitations of softmax attention, several subquadratic recurrent operators have been developed. This work includes models such as Mam…
Active Human Feedback Collection via Neural Contextual Dueling Bandits
Arun Verma, Xiaoqiang Lin, Zhongxiang Dai +2
Collecting human preference feedback is often expensive, leading recent works to develop principled algorithms to select them more efficiently. However, these works assume that the…
Data value estimation on private gradients
Zijian Zhou, Xinyi Xu, Daniela Rus +1
For gradient-based machine learning (ML) methods commonly adopted in practice such as stochastic gradient descent, the de facto differential privacy (DP) technique is perturbing th…