Search papers, labs, and topics across Lattice.
Lenovo, Beijing, China, Hanhui Li, Xuan Huang, Wanquan Liu, Xiaodan Liang, Chenqiang Gao are with the School of Intelligent Systems Engineering, Shenzhen Campus of Sun Yat-sen University, P.R. China, 518107. Yuhao Cheng, Long Chen, and Yiqiang Yan are with the Lenovo Research Group, Shenzhen, P.R. China, 518038.∗ Hanhui Li and Xuan Huang contribute equally.† Chenqiang Gao is the corresponding author
2
0
4
AdaZoom-GUI achieves SOTA GUI grounding by adaptively zooming in on small elements and refining ambiguous instructions, outperforming even larger models.
Reconstructing realistic 3D hand avatars from messy, real-world video just got a whole lot better thanks to a new method that explicitly models and suppresses visual "noise" like motion blur and object interactions.
