Kaixiang Zhao

The paper introduces GraphIP-Bench, a unified benchmark that demonstrates that stealing Graph Neural Networks (GNNs) is relatively easy, and existing defenses often fail to maintain their integrity after the model is successfully extracted.

LARK introduces a novel learnability-grounded approach for selecting reasoning trajectories, significantly improving the efficiency of reasoning distillation by prioritizing trajectories that the student model can learn from.

TIGER is an inference-time framework that uses graph-based evidence routing to independently assess and repair unsupported facts (hallucinations) in multimodal generation.