2 papers
cs.CV2026
Beyond Text Conditioning: A Systematic Study of MLLM-DiT Fusion for Video Generation
Yanbo Ding, Yijia Fan, Caihua Shan +8
Diffusion Transformers (DiTs) have become the dominant paradigm for high-fidelity video generation, yet their ability to perform high-level semantic planning remains limited. While…
math.AP2026
Chemotaxis compressible Navier-Stokes equations with density-dependent viscosity modeling vascular network formation
Ansgar Jüngel, Flora Philipp
The existence of global weak solutions to the compressible Navier-Stokes equations for the density of endothelial cells and their velocity, coupled to a reaction-diffusion equation…