Search papers, labs, and topics across Lattice.
University of Southern California
4
0
6
Incorporating spectral structural priors into uncertain knowledge graph completion can dramatically enhance prediction accuracy and training stability without adding extra parameters.
Identical embeddings for non-isomorphic graphs reveal the limitations of global-attention graph transformers in capturing the nuanced structure of mixed-integer linear programs.
Women in science face a tilted playing field where institutional prestige amplifies success unevenly, favoring men even at lower-ranked institutions.
LLMs struggle with affordance reasoning, lagging behind humans by 20 points, but a new method can boost their performance significantly.
