activity
20242026
collaborators

9 papers

cs.CL2026

MineDraft: A Framework for Batch Parallel Speculative Decoding

Zhenwei Tang, Arun Verma, Zijian Zhou +4

Speculative decoding (SD) accelerates large language model inference by using a smaller draft model to propose draft tokens that are subsequently verified by a larger target model.…

cs.CL2026

MeMo: Memory as a Model

Ryan Wei Heng Quek, Sanghyuk Lee, Alfred Wei Lun Leong +6

Large language models (LLMs) achieve strong performance across a wide range of tasks, but remain frozen after pretraining until subsequent updates. Many real-world applications req…

cs.LG2026

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…

cs.LG2026

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…

cs.CL2025

MEM1: Learning to Synergize Memory and Reasoning for Efficient Long-Horizon Agents

Zijian Zhou, Ao Qu, Zhaoxuan Wu +6

Modern language agents must operate over long-horizon, multi-turn interactions, where they retrieve external information, adapt to observations, and answer interdependent queries.…

cs.LG2025

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…