JanusFlow: Harmonizing Autoregression and Rectified Flow for Unified Multimodal Understanding and Generationby Yiyang Ma, Xingchao…
PointCG: Self-supervised Point Cloud Learning via Joint Completion and Generationby Yun Liu, Peng Li, Xuefeng…
DiMSUM: Diffusion Mamba – A Scalable and Unified Spatial-Frequency Method for Image Generationby Hao Phung,…
On Improved Conditioning Mechanisms and Pre-training Strategies for Diffusion Modelsby Tariq Berrada Ifriqi, Pietro Astolfi,…
Gradient-Guided Conditional Diffusion Models for Private Image Reconstruction: Analyzing Adversarial Impacts of Differential Privacy and…
TypeScore: A Text Fidelity Metric for Text-to-Image Generative Modelsby Georgia Gabriela Sampaio, Ruixiang Zhang, Shuangfei…
Towards Visual Text Design Transfer Across Languagesby Yejin Choi, Jiwan Chung, Sumin Shim, Giyeong Oh,…
Ali-AUG: Innovative Approaches to Labeled Data Augmentation using One-Step Diffusion Modelby Ali Hamza, Aizea Lojo,…
FairQueue: Rethinking Prompt Learning for Fair Text-to-Image Generationby Christopher T.H Teo, Milad Abdollahzadeh, Xinda Ma,…
TextureMeDefect: LLM-based Defect Texture Generation for Railway Components on Mobile Devicesby Rahatara Ferdousi, M. Anwar…