Search papers, labs, and topics across Lattice.
Kling Team, Kuaishou Technology
5
0
4
GIVE achieves reliable geometric edits in video editing by unifying object-state specifications, overcoming traditional challenges in generative workflows.
CineCap achieves a new state of the art in cinematographic video captioning by effectively balancing descriptive completeness with factual accuracy through innovative structured reasoning techniques.
UnityShots achieves unprecedented cross-shot coherence in multi-shot video generation, outperforming open-source benchmarks and rivaling top closed-source systems.
VLMs can outperform traditional problem-solving roles by serving as adaptive teachers, leading to a dramatic 16.7-point boost in video reasoning performance.
Amodal SAM unlocks zero-shot amodal segmentation by adapting the Segment Anything Model (SAM) to infer complete object shapes, even in the presence of occlusions.
