2 papers
cs.LG2026
Resource-Efficient Pruning for Transformer via Low-Rank Importance Estimation
Peng Liu, Huibing Zeng, Yiqun Zhang +2
With the rapid development of large-scale pre-trained language models based on Transformer architectures, their high computational and memory costs have become a major obstacle to…
cs.CV2024
BitQ: Tailoring Block Floating Point Precision for Improved DNN Efficiency on Resource-Constrained Devices
Yongqi Xu, Yujian Lee, Gao Yi +6
Deep neural networks (DNNs) are powerful for cognitive tasks such as image classification, object detection, and scene segmentation. One drawback however is the significant high co…