Hangjie Yuan

Lumos-Nexus is a training-efficient framework that enhances video generation quality by progressively bridging generation from a lightweight model to a high-fidelity generator in a shared latent space, without sacrificing reasoning capabilities.

The paper proposes a novel render-free framework that conditions video diffusion models directly on compressed 3D human mesh tokens, enabling robust 3D-aware human motion control without relying on rendered 2D guidance.

This paper introduces ClinFusion, a vision-centric multimodal large language model designed for holistic medical understanding, featuring a Cascade Spatial-Aware Locality Fusion operator and a vision-grounded evaluation framework.