4 papers
Rethinking Test Time Scaling for Flow-Matching Generative Models
Qingtao Yu, Changlin Song, Minghao Sun +6
The performance of text-to-image diffusion models may be improved at test-time by scaling computation to search for a generated image that maximizes a given reward function. While…
AutoRefiner: Improving Autoregressive Video Diffusion Models via Reflective Refinement Over the Stochastic Sampling Path
Zhengyang Yu, Akio Hayakawa, Masato Ishii +4
Autoregressive video diffusion models (AR-VDMs) show strong promise as scalable alternatives to bidirectional VDMs, enabling real-time and interactive applications. Yet there remai…
RetinaGuard: Obfuscating Retinal Age in Fundus Images for Biometric Privacy Preserving
Zhengquan Luo, Chi Liu, Dongfu Xiao +3
The integration of AI with medical images enables the extraction of implicit image-derived biomarkers for a precise health assessment. Recently, retinal age, a biomarker predicted…
FuseAnyPart: Diffusion-Driven Facial Parts Swapping via Multiple Reference Images
Zheng Yu, Yaohua Wang, Siying Cui +3
Facial parts swapping aims to selectively transfer regions of interest from the source image onto the target image while maintaining the rest of the target image unchanged. Most st…