Haoge Deng

3d reconstruction (1) zero-shot learning (1) self-supervised learning (1) multimodal learning (1) video understanding (1) visual reasoning (1) diffusion model (1) 3d generation (1) multi-view diffusion (1) zero-shot generation (1) model efficiency (1) view synthesis (1) multi-view generation (1) visual language model (1) 3d creation (1) pose-free training (1) visual conditioning (1) web-scale video (1) encoder-free vision-language model (1) visual conditional (1)