Search papers, labs, and topics across Lattice.
University of Texas at Austin
6
0
10
LLMs are not just tools; they are reshaping the very fabric of research, but they also introduce systemic risks that could undermine scientific integrity.
Unsupervised graph anomaly detection is now possible across diverse graphs, achieving zero-shot generalization without relying on labeled data or few-shot examples.
Uncover tax evasion rings with a novel graph neural network that leverages related party transaction data to significantly outperform existing detection methods.
Forget complex sequence models: this new method efficiently captures temporal dynamics in graphs by contrasting node representations across different timespans.
Achieve more reliable ADAS by using a physics-informed neural network that leverages damper characteristics to estimate wheel load more accurately than existing methods.
Mimicking clinical diagnosis, this method boosts medical image classification by adaptively retrieving and reasoning over similar cases represented in multimodal knowledge graphs, leading to more accurate and explainable predictions.
