Search papers, labs, and topics across Lattice.
Zhejiang University
3
0
5
Mimicking clinical diagnostic thinking with counterfactual reasoning boosts medical video diagnosis accuracy by up to 10.2%.
Representing environments as semantically-grouped 3D Gaussians dramatically improves Vision-Language Navigation in unseen environments.
Overcoming perceptual uncertainty in vision-language navigation is now possible by explicitly modeling geometric, semantic, and appearance uncertainty with a novel Uncertainty-Aware Gaussian Map.
