3 papers
cs.CV2025
FRAP: Faithful and Realistic Text-to-Image Generation with Adaptive Prompt Weighting
Liyao Jiang, Negar Hassanpour, Mohammad Salameh +4
Text-to-image (T2I) diffusion models have demonstrated impressive capabilities in generating high-quality images given a text prompt. However, ensuring the prompt-image alignment r…
cs.LG2024
Applying Graph Explanation to Operator Fusion
Keith G. Mills, Muhammad Fetrat Qharabagh, Weichen Qiu +5
Layer fusion techniques are critical to improving the inference efficiency of deep neural networks (DNN) for deployment. Fusion aims to lower inference costs by reducing data trans…
cs.CV2024
QuaSeDiMo: Quantifiable Quantization Sensitivity of Diffusion Models
Keith G. Mills, Mohammad Salameh, Ruichen Chen +3
Diffusion Models (DM) have democratized AI image generation through an iterative denoising process. Quantization is a major technique to alleviate the inference cost and reduce the…