4 papers
ParaUni: Enhance Generation in Unified Multimodal Model with Reinforcement-driven Hierarchical Parallel Information Interaction
Jiangtong Tan, Lin Liu, Jie Huanng +3
Unified multimodal models significantly improve visual generation by combining vision-language models (VLMs) with diffusion models. However, existing methods struggle to fully bala…
InfoScale: Unleashing Training-free Variable-scaled Image Generation via Effective Utilization of Information
Guohui Zhang, Jiangtong Tan, Linjiang Huang +4
Diffusion models (DMs) have become dominant in visual generation but suffer performance drop when tested on resolutions that differ from the training scale, whether lower or higher…
Adaptive Dropout: Unleashing Dropout across Layers for Generalizable Image Super-Resolution
Hang Xu, Wei Yu, Jiangtong Tan +2
Blind Super-Resolution (blind SR) aims to enhance the model's generalization ability with unknown degradation, yet it still encounters severe overfitting issues. Some previous meth…
FreePCA: Integrating Consistency Information across Long-short Frames in Training-free Long Video Generation via Principal Component Analysis
Jiangtong Tan, Hu Yu, Jie Huang +2
Long video generation involves generating extended videos using models trained on short videos, suffering from distribution shifts due to varying frame counts. It necessitates the…