6 papers
Endless World: Real-Time 3D-Aware Long Video Generation
Ke Zhang, Yiqun Mei, Jiacong Xu +1
Producing long, coherent video sequences with stable 3D structure remains a major challenge, particularly in streaming scenarios. Motivated by this, we introduce Endless World, a r…
FreeViS: Training-free Video Stylization with Inconsistent References
Jiacong Xu, Yiqun Mei, Ke Zhang +1
Video stylization plays a key role in content creation, but it remains a challenging problem. Naïvely applying image stylization frame-by-frame hurts temporal consistency and reduc…
Think Before You Diffuse: Infusing Physical Rules into Video Diffusion
Ke Zhang, Cihan Xiao, Jiacong Xu +2
Recent video diffusion models have demonstrated their great capability in generating visually-pleasing results, while synthesizing the correct physical effects in generated videos…
Filter Images First, Generate Instructions Later: Pre-Instruction Data Selection for Visual Instruction Tuning
Bardia Safaei, Faizan Siddiqui, Jiacong Xu +2
Visual instruction tuning (VIT) for large vision-language models (LVLMs) requires training on expansive datasets of image-instruction pairs, which can be costly. Recent efforts in…
Towards Zero-Shot Anomaly Detection and Reasoning with Multimodal Large Language Models
Jiacong Xu, Shao-Yuan Lo, Bardia Safaei +2
Zero-Shot Anomaly Detection (ZSAD) is an emerging AD paradigm. Unlike the traditional unsupervised AD setting that requires a large number of normal samples to train a model, ZSAD…
XYScanNet: A State Space Model for Single Image Deblurring
Hanzhou Liu, Chengkai Liu, Jiacong Xu +2
Deep state-space models (SSMs), like recent Mamba architectures, are emerging as a promising alternative to CNN and Transformer networks. Existing Mamba-based restoration methods p…