Search papers, labs, and topics across Lattice.
Shanghai Jiao Tong University
3
0
6
11
Current vision-language models struggle with process understanding in robotic manipulation, but targeted post-training can yield significant improvements.
Revisiting spatial reasoning allows models to correct initial hypotheses with new perspectives, dramatically enhancing their accuracy in complex environments.
Ditch the feature extraction pipeline: GenMask directly generates segmentation masks with a diffusion transformer, achieving SOTA results by harmonizing mask and image generation in a single model.
