Ninglu Shao — accepted AI-conference papers

2025

Long Context Compression with Activation Beacon

Peitian Zhang, Zheng Liu, Shitao Xiao, Ninglu Shao, Qiwei Ye, Zhicheng Dou

ICLR 2025poster

Long context compression is a critical research problem due to its significance in reducing the high computational and memory costs associated with LLMs. In this paper, we propose Activation Beacon, a plug-in module for transformer-based LLMs that targets effective, efficient, and flexible compressi…

Cited by 12 Source ↗PDF ↗code ↗Scholar ↗

2023

Reward Imputation with Sketching for Contextual Batched Bandits

Xiao Zhang, Ninglu Shao, Zihua Si, Jun Xu, Wenhan Wang, Hanjing Su +1

NeurIPS 2023poster

Contextual batched bandit (CBB) is a setting where a batch of rewards is observed from the environment at the end of each episode, but the rewards of the non-executed actions are unobserved, resulting in partial-information feedback. Existing approaches for CBB often ignore the rewards of the non-ex…

Cited by 0 Source ↗PDF ↗Scholar ↗