2 citations · 3 across the 9 of their papers we have counts for
5 papers · 1 filter
MeteoVerse: Unified Weather-Controllable Video World Model
Renlong Wu, Guanqiao Wang, Xuan Shang +5
Video world models aim to predict future content from an observed scene while following prescribed camera motion. Real-world scene evolution is determined not only by changes in vi…
CompAdapt: Adaptable Composite Motion Modeling for Physics-Consistent Text-to-Video Generation
Haoran Qin, Renlong Wu, Tianyu Huang +3
While diffusion-based text-to-video (T2V) models have demonstrated impressive capability in generating realistic and temporally coherent videos, they often fail to respect fundamen…
4DHumanDiff: Direct Text-to-4DGS Generation for Consistent 360-Degree Dynamic Humans
Renlong Wu, Haoran Chen, Yuxiang Wei +3
Generating high-quality 360-degree dynamic human assets from text prompts is challenging. Existing methods usually synthesize monocular or multi-view videos first and then fit a 4D…
Typical entanglement in anyon chains: Page curves beyond Lie group symmetries
Yale Yauk, Lucas Hackl, Alexander Hahn
We study bipartite entanglement statistics in one-dimensional anyon chains, whose Hilbert spaces are constrained by fusion rules of unitary pre-modular categories. Our setup genera…
Lie Flow: Video Dynamic Fields Modeling and Predicting with Lie Algebra as Geometric Physics Principle
Weidong Qiao, Wangmeng Zuo, Hui Li
Modeling 4D scenes requires capturing both spatial structure and temporal motion, which is challenging due to the need for physically consistent representations of complex rigid an…