Xun-Kai Li

A single benchmark now rigorously tests how AI models interpret scientific figures to predict, explain, and discover biological mechanisms, moving beyond mere simulation.

LION achieves unprecedented performance in multimodal graph tasks by effectively aligning and fusing modalities through a novel Clifford algebra framework.

Neglecting the structural differences in candidate negatives can lead to suboptimal recommendations, but SAHC-NS adapts to these variations, enhancing sample quality and model performance.

OpenRTAG reveals that traditional GNNs struggle significantly more than LLM-GNNs under realistic data quality degradation, highlighting critical vulnerabilities in graph learning models.

FedLAB achieves up to 7.53% improvement over existing methods while ensuring that multimodal graph knowledge remains traceable and privacy-preserving.

Long-tailed distributions in federated graph learning can be effectively tackled with a dual decoupling approach that boosts minority node performance without compromising majority class accuracy.

Missing modalities in federated learning can be effectively synthesized, leading to substantial performance gains in multimodal tasks.

MAGE-RAG achieves a remarkable 52.75% accuracy on LongDocURL by intelligently balancing evidence coverage and context noise in long-document multimodal QA.

PRISM boosts performance in modality-deficient federated graph learning by intelligently retrieving and integrating missing modalities from the entire federation.

By explicitly modeling the temporal decay of user-item interactions, TFPS constructs more reliable positive samples, leading to significant improvements in recommendation accuracy compared to methods that focus solely on negative sampling.