3 papers
cs.CV2026
MedVAR: Towards Scalable and Efficient Medical Image Generation via Next-scale Autoregressive Prediction
Zhicheng He, Yunpeng Zhao, Junde Wu +5
Medical image generation is pivotal in applications like data augmentation for low-resource clinical tasks and privacy-preserving data sharing. However, developing a scalable gener…
cs.LG2025
Sculpting Features from Noise: Reward-Guided Hierarchical Diffusion for Task-Optimal Feature Transformation
Nanxu Gong, Zijun Li, Sixun Dong +4
Feature Transformation (FT) crafts new features from original ones via mathematical operations to enhance dataset expressiveness for downstream models. However, existing FT methods…
cs.CV2025
TMCIR: Token Merge Benefits Composed Image Retrieval
Chaoyang Wang, Zeyu Zhang, Long Teng +2
Composed Image Retrieval (CIR) retrieves target images using a multi-modal query that combines a reference image with text describing desired modifications. The primary challenge i…