3 papers
cs.CV2026
ASTRA: Enhancing Multi-Subject Generation with Retrieval-Augmented Pose Guidance and Disentangled Position Embedding
Tianze Xia, Zijian Ning, Zonglin Zhao +1
Subject-driven image generation has shown great success in creating personalized content, but its capabilities are largely confined to single subjects in common poses. Current appr…
cs.CV2026
ITO: Images and Texts as One via Synergizing Multiple Alignment and Training-Time Fusion
Hanpeng Liu, Yaqian Li, Zidan Wang +6
Image-text contrastive pretraining has become a dominant paradigm for visual representation learning, yet existing methods often yield representations that remain partially organiz…
cs.CL2026
Order Is Not Layout: Order-to-Space Bias in Image Generation
Yongkang Zhang, Zonglin Zhao, Yuechen Zhang +3
We study a systematic bias in modern image generation models: the mention order of entities in text spuriously determines spatial layout and entity--role binding. We term this phen…