Louis Feng — accepted AI-conference papers

2025

MQuAKE-Remastered: Multi-Hop Knowledge Editing Can Only Be Advanced with Reliable Evaluations

Shaochen Zhong, Yifan Lu, Lize Shao, Bhargav Bhushanam, Xiaocong Du, Yixin Wan +10

ICLR 2025spotlight

Large language models (LLMs) can give out erroneous answers to factually rooted questions either as a result of undesired training outcomes or simply because the world has moved on after a certain knowledge cutoff date. Under such scenarios, *knowledge editing* often comes to the rescue by deliverin…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗

2022

DreamShard: Generalizable Embedding Table Placement for Recommender Systems

Daochen Zha, Louis Feng, Qiaoyu Tan, Zirui Liu, Kwei-Herng Lai, Bhargav Bhushanam +3

NeurIPS 2022accept

We study embedding table placement for distributed recommender systems, which aims to partition and place the tables on multiple hardware devices (e.g., GPUs) to balance the computation and communication costs. Although prior work has explored learning-based approaches for the device placement of co…

Cited by 38 Source ↗PDF ↗code ↗Scholar ↗