3 papers
cs.RO2026
RoboPhys-3D: A Comprehensive Embodied World Model Evaluation via 3D Reconstruction
Tianyi Wang, Jiazhou Chen, Yiming Xu +7
Video world models increasingly serve as data engines, action planners, and simulators for embodied AI, but conventional embodied world model (EWM) benchmarks lack a unified 3D-gro…
cs.CV2026
Latent Inter-Frame Pruning: A Training-Free Method Bridging Traditional Video Compression and Modern Diffusion Transformers for Efficient Generation
Dennis Menn, Chih-Hsien Chou
Video generation, while capable of generating realistic videos, is computationally expensive and slow, prohibiting real-time applications. In this paper, we observe that video late…
cs.CV2024
Source-free Domain Adaptation for Video Object Detection Under Adverse Image Conditions
Xingguang Zhang, Chih-Hsien Chou
When deploying pre-trained video object detectors in real-world scenarios, the domain gap between training and testing data caused by adverse image conditions often leads to perfor…