Search papers, labs, and topics across Lattice.
4
0
8
This paper proposes MOCO, a novel diffusion-based framework capable of processing multiple simultaneous inputs, including speech audio, text descriptions, and trajectory data, to generate coherent and lifelike motions without requiring aligned multimodal data.
SparseCtrl-HOI slashes annotation costs while generating high-quality HOI videos, revolutionizing the landscape of AI-driven e-commerce content creation.
Calibration-data composition can dramatically enhance quantization performance, with 3.5-bit models outperforming traditional 4-bit baselines by over 20 points.
A single adaptive framework can boost the efficiency of zeroth-order optimization by up to 3x without increasing memory usage.
