Search papers, labs, and topics across Lattice.
3
0
4
3
Achieve real-time video understanding with transparent reasoning: \model{} aligns response timing with visual evidence, offering a breakthrough for online video LLMs.
By unifying geometric guidance across representation, architecture, and loss, UniGeo achieves unprecedented camera control and cross-view consistency in image editing, leaving previous fragmented approaches in the dust.
Counterintuitively, cropping and resizing a region of interest before refinement dramatically improves the fidelity of local detail restoration in diffusion models, enabling near-perfect background preservation.
