Search papers, labs, and topics across Lattice.
Affiliation:, The University of Hong Kong
6
0
6
18
PartLLM is introduced, a unified multimodal model that formulates 3D part segmentation as autoregressive semantic decomposition that supports text-guided part segmentation, interactive segmentation, and full-shape semantic decomposition with controllable granularity within a single model.
Ms.Forcing achieves a 39.6% speedup in streaming video generation while significantly enhancing quality by intelligently adapting spatial granularity to noise levels.
RoboDojo reveals that integrating simulation and real-world tasks can significantly enhance the evaluation of robot manipulation policies, bridging the gap between theoretical performance and practical deployment.
Animating 4D shapes just got easier: GaussiAnimate's "Skelebones" can reanimate unseen poses with 17% better PSNR than standard methods.