Search papers, labs, and topics across Lattice.
Shenzhen Technology University 鈭桬qual contribution
4
0
5
6
Models that generate convincing anomaly descriptions often fail to accurately track the corresponding instances, exposing a critical gap in video anomaly understanding.
TTA can boost accuracy but often at the cost of calibration, and ZAEC is the key to restoring reliable confidence without labeled data.
GeniWorld achieves robust zero-shot generalization in robotic manipulation, outperforming traditional models even with minimal training data.
ChainVLA achieves a remarkable 62.8% success rate on long-horizon manipulation tasks by seamlessly chaining vision-language-action queries through a unified execution state.
