Search papers, labs, and topics across Lattice.
4
0
7
3
Teacher Prediction Refinement Distillation (TPRD), a plug-and-play module that refines teacher predictions before distillation by exploiting stage-wise prediction information, and Maximum Dark Knowledge Preservation (MDKP), which selectively refines target-class logits while retaining non-target relations.
Achieving state-of-the-art motion generation, DeMoDiff allows for unprecedented control over individual body parts while maintaining high-quality outputs.
A unified framework that simultaneously enhances interaction understanding and generation, achieving state-of-the-art results in multimodal human-human interaction analysis.
Enfold redefines how we leverage world generative models, enabling ultra-efficient control that adapts dynamically to real-time changes in the environment.
