5 papers
Selective Coupling of Decoupled Informative Regions: Masked Attention Alignment for Data-Free Quantization of Vision Transformers
Biao Qian, Yang Wang, Yong Wu +1
Data-Free Quantization (DFQ) addresses data security concerns by synthesizing samples, without accessing real data. It has garnered increasing attention in the context of Vision Tr…
AI-T2I: Aggregating-and-Isolating Cross-Attention to Diffusion Models for Text-to-Image Synthesis
Shipeng Cao, Biao Qian, Haipeng Liu +2
Text-to-image synthesis has made significant progress, benefiting from the strong generative capabilities of diffusion models. However, these models struggle to achieve precise tex…
Mostly Text, Smart Visuals: Asymmetric Text-Visual Pruning for Large Vision-Language Models
Sijie Li, Biao Qian, Jungong Han
Network pruning is an effective technique for enabling lightweight Large Vision-Language Models (LVLMs), which primarily incorporates both weights and activations into the importan…
Thinking inside the Convolution for Image Inpainting: Reconstructing Texture via Structure under Global and Local Side
Haipeng Liu, Yang Wang, Biao Qian +2
Image inpainting has earned substantial progress, owing to the encoder-and-decoder pipeline, which is benefited from the Convolutional Neural Networks (CNNs) with convolutional dow…
Coarse-to-Fine Lightweight Meta-Embedding for ID-Based Recommendation
Yang Wang, Haipeng Liu, Zeqian Yi +2
The state-of-the-art recommendation systems have shifted the attention to efficient recommendation, e.g., on-device recommendation, under memory constraints. To this end, the exist…