Data Party THU

Jul 31, 2025 · Artificial Intelligence

How LaVin-DiT Revolutionizes Vision Generation with ST‑VAE and Joint Diffusion Transformer

The LaVin-DiT paper introduces a large‑scale vision diffusion transformer that combines a spatiotemporal variational auto‑encoder, a joint diffusion transformer with full‑sequence joint attention, and 3D rotary position encoding to enable unified, efficient generation across diverse visual tasks such as segmentation and video prediction.