Search papers, labs, and topics across Lattice.
Nankai University
6
0
9
Ultra-low token pruning can achieve 92.1% of peak performance with only 16 visual tokens, thanks to a novel approach that preserves distribution consistency.
Z-Reward achieves 41.3% better human preference alignment in text-to-image generation by transforming complex reasoning into efficient score distributions.
Achieving pose-controllable object insertion with high visual fidelity, DIRECT redefines the boundaries of 2D image synthesis by integrating 3D manipulation.
RoadGIE's connectivity-aware prompts and expert-guided interaction paradigm leapfrog traditional point-and-box prompting, enabling more accurate and topologically consistent road extraction from aerial imagery.
Achieve up to 2.5X faster video object removal by focusing DiT computations only on the essential tokens dictated by the mask.
Skip the bulky bidirectional teacher: this new method trains a fast, causal audio-video generator directly, slashing sampling steps while maintaining top-tier quality.
