2 papers
cs.LG2026
Prune-Quantize-Distill: An Ordered Pipeline for Efficient Neural Network Compression
Longsheng Zhou, Yu Shen
Modern deployment often requires trading accuracy for efficiency under tight CPU and memory constraints, yet common compression proxies such as parameter count or FLOPs do not reli…
cs.CV2025
UNEM: UNrolled Generalized EM for Transductive Few-Shot Learning
Long Zhou, Fereshteh Shakeri, Aymen Sadraoui +3
Transductive few-shot learning has recently triggered wide attention in computer vision. Yet, current methods introduce key hyper-parameters, which control the prediction statistic…