Zhexi Zhang — accepted AI-conference papers

2023

MobileNMT: Enabling Translation in 15MB and 30ms

Ye Lin, Xiaohui Wang, Zhexi Zhang, Mingxuan Wang, Tong Xiao, Jingbo Zhu

ACL 2023industry

Deploying NMT models on mobile devices is essential for privacy, low latency, and offline scenarios. For high model capacity, NMT models are rather large. Running these models on devices is challenging with limited storage, memory, computation, and power consumption. Existing work either only focuse…

Cited by 1 Source ↗PDF ↗code ↗Scholar ↗

2023

ROME: Robustifying Memory-Efficient NAS via Topology Disentanglement and Gradient Accumulation

Xiaoxing Wang, Xiangxiang Chu, Yuda Fan, Zhexi Zhang, Bo Zhang, Xiaokang Yang +1

ICCV 2023poster

Albeit being a prevalent architecture searching approach, differentiable architecture search (DARTS) is largely hindered by its substantial memory cost since the entire supernet resides in the memory. This is where the single-path DARTS comes in, which only chooses a single-path submodel at each ste…

Cited by 12 PDF ↗Scholar ↗