Search papers, labs, and topics across Lattice.
VinUniversity, Hanoi, Vietnam
5
0
10
ChemBack reveals that even with rigorous admission protocols, chemically valid backdoors can still pose significant risks to molecular graph neural networks.
Majority aggregation in RLHF can overlook 79% of culturally valid responses, risking misalignment in diverse societies.
Just because an AI can identify the trigger for an emotion doesn't mean it understands *why* that emotion occurred – and current benchmarks are misleading us.
Forget disjointed approaches: OneHOI's unified diffusion transformer generates and edits human-object interactions with unprecedented control and realism.
Forget static cues: VAGNet grounds 3D object affordances by watching how humans actually use them in videos, significantly improving localization of interaction regions.
