Search papers, labs, and topics across Lattice.
University of Electronic Science and Technology of China
5
0
8
Reasoning VLMs falter under semantic distractions, often mistaking irrelevant cues for evidence, which can lead to incorrect answers.
MAGIS transforms strabismus diagnosis from a black-box process into a transparent, evidence-driven framework that boosts accuracy and clinical reliability.
Projector Drift reveals a hidden pitfall in omni-modal retrieval, where fusing modalities can inadvertently degrade performance in audio tasks.
Quantum policies can be trained to be significantly safer and more efficient than classical ones by minimizing reliance on safety filters, revealing the true source of safety in learned controllers.
RACL slashes false veto rates to nearly zero by allowing for repairs before outright rejection, transforming how we approach constraint learning in contextual decisions.
