6 papers
Compress Then Adapt? No, Do It Together via Task-aware Union of Subspaces
Jingze Ge, Yun Liu, Xue Geng +4
Adapting large pretrained models to diverse tasks is now routine, yet the two dominant strategies of parameter-efficient fine-tuning (PEFT) and low-rank compression are typically c…
Joint Architecture-Token-Bitwidth Multi-Axis Optimization of Vision Transformers for Semiconductor IC Packaging
Phat Nguyen, Xue Geng, Kaixin Xu +3
Vision Transformers (ViTs) have achieved strong performance in visual recognition, yet their deployment in resource-constrained industrial environments remains limited. Some main c…
LPViT: Low-Power Semi-structured Pruning for Vision Transformers
Kaixin Xu, Zhe Wang, Chunyun Chen +7
Vision transformers have emerged as a promising alternative to convolutional neural networks for various image analysis tasks, offering comparable or superior performance. However,…
An Efficient 3D Convolutional Neural Network with Channel-wise, Spatial-grouped, and Temporal Convolutions
Zhe Wang, Xulei Yang
There has been huge progress on video action recognition in recent years. However, many works focus on tweaking existing 2D backbones due to the reliance of ImageNet pretraining, w…
DM3D: Distortion-Minimized Weight Pruning for Lossless 3D Object Detection
Kaixin Xu, Qingtian Feng, Hao Chen +6
Applying deep neural networks to 3D point cloud processing has attracted increasing attention due to its advanced performance in many areas, such as AR/VR, autonomous driving, and…
From Algorithm to Hardware: A Survey on Efficient and Safe Deployment of Deep Neural Networks
Xue Geng, Zhe Wang, Chunyun Chen +10
Deep neural networks (DNNs) have been widely used in many artificial intelligence (AI) tasks. However, deploying them brings significant challenges due to the huge cost of memory,…