Search papers, labs, and topics across Lattice.
Zhejiang University, Shanghai Innovation Institute, The Hong Kong University of Science and Technology (
4
0
8
GGR transforms the landscape of open-set semi-supervised learning by ensuring that auxiliary gradients enhance rather than conflict with supervised updates.
Uncover hidden connections between broad biomedical knowledge and specific experimental data with SCENE, a framework that transforms general knowledge into testable, scenario-grounded hypotheses.
You can generate high-quality molecules that hit two targets at once, without the cost of retraining your generative model.
Stop training black-box reward models: VL-MDR offers a transparent alternative that surfaces *why* a VLM is getting a certain reward, opening the door to more targeted alignment.
