most citedAuto-ViT-Acc: An FPGA-Aware Automatic Acceleration Framework for Vision Transformer with Mixed-Scheme Quantization

6 citations · 13 across the 6 of their papers we have counts for

collaborators

6 papers

cs.CV2024

Efficient Training with Denoised Neural Weights

Yifan Gong, Zheng Zhan, Yanyu Li +6

Good weight initialization serves as an effective measure to reduce the training cost of a deep neural network (DNN) model. The choice of how to initialize parameters is challengin…

cs.CV2024

TextCraftor: Your Text Encoder Can be Image Quality Controller

Yanyu Li, Xian Liu, Anil Kag +6

Diffusion-based text-to-image generative models, e.g., Stable Diffusion, have revolutionized the field of content generation, enabling significant advancements in areas like image…

hep-ph20245 cited

Searching for the light leptophilic gauge boson via four-lepton final states at the CEPC

Chong-Xing Yue, Yan-Yu Li, Mei-Shu-Yu Wang +1

We investigate the possibility of detecting the leptophilic gauge boson predicted by the model via the processes $e^+e^-\rightarrow\ell^+\ell^-Z_x(Z_x\righta…

cs.CV20226 cited

Auto-ViT-Acc: An FPGA-Aware Automatic Acceleration Framework for Vision Transformer with Mixed-Scheme Quantization

Zhengang Li, Mengshu Sun, Alec Lu +9

Vision transformers (ViTs) are emerging with significantly improved accuracy in computer vision tasks. However, their complex architecture and enormous computation/storage demand i…

cs.CV20222 cited

Compiler-Aware Neural Architecture Search for On-Mobile Real-time Super-Resolution

Yushu Wu, Yifan Gong, Pu Zhao +7

Deep learning-based super-resolution (SR) has gained tremendous popularity in recent years because of its high image quality performance and wide application scenarios. However, pr…

hep-ph2022

Searching for the charged-current non-standard neutrino interactions at the colliders

Chongxing Yue, Xuejia Cheng, Yueqi Wang +1

Considering the theoretical constraints on the charged-current (CC) non-standard neutrino interaction (NSI) parameters in a simplified model, we study the sensitivities of the…