6 citations · 29 across the 30 of their papers we have counts for
4 papers · 1 filter
Learning Disentangled Identifiers for Action-Customized Text-to-Image Generation
Siteng Huang, Biao Gong, Yutong Feng +4
This study focuses on a novel task in text-to-image (T2I) generation, namely action customization. The objective of this task is to learn the co-existing action from limited data a…
Check, Locate, Rectify: A Training-Free Layout Calibration System for Text-to-Image Generation
Biao Gong, Siteng Huang, Yutong Feng +3
Diffusion models have recently achieved remarkable progress in generating realistic images. However, challenges remain in accurately understanding and synthesizing the layout requi…
VGDiffZero: Text-to-image Diffusion Models Can Be Zero-shot Visual Grounders
Xuyang Liu, Siteng Huang, Yachen Kang +2
Large-scale text-to-image diffusion models have shown impressive capabilities for generative tasks by leveraging strong vision-language alignment from pre-training. However, most v…
Troika: Multi-Path Cross-Modal Traction for Compositional Zero-Shot Learning
Siteng Huang, Biao Gong, Yutong Feng +3
Recent compositional zero-shot learning (CZSL) methods adapt pre-trained vision-language models (VLMs) by constructing trainable prompts only for composed state-object pairs. Relyi…