Search papers, labs, and topics across Lattice.
Shanghai Jiao Tong University
3
0
5
Unified multimodal models can bootstrap both visual generation and perceptual understanding purely from text prompts by treating their own generative flow trajectories as self-supervised grounding signals.
Imagine turning any single-view video into a fully explorable, dynamic 4D scene – this paper gets us closer with a novel diffusion-based approach and a new large-scale dataset.
Finally, a method disentangles dynamic egocentric scenes into background, hand, and object components, enabling fine-grained understanding and editing.
