الباحثون

Zhaoxian Wu

المنشورات 2

نسخة أولية وصول مفتوح

Robust Parameter-Efficient LLM Adaptation on Analog Hardware

Jindan Li, Zhaoxian Wu, Tianyi Chen · 2026

Analog in-memory computing is a promising platform for on-device execution of large language models because it performs matrix--vector multiplications (MVMs) in memory and in parallel, reducing data movement. However, limited digital-to-analog converter precision, input noise, and finite conductance states can degrade …

نسخة أولية وصول مفتوح

Making Analog Training Scale: Co-Designing Mapping, Optimizer, and Converters

Zhaoxian Wu, Tayfun Gokmen, Omobayode Fagbohungbe وآخرون · 2026

Analog in-memory computing (AIMC) offers an alternative for model training by executing matrix operations directly where weights are stored. However, scaling AIMC to train modern deep models remains an open challenge due to severe hardware non-idealities, including physical weights with finite dynamic range and write g …

المؤلفون المشاركون