Search papers, labs, and topics across Lattice.
Beijing Institute of Technology
6
0
7
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.
A unified runtime boundary and time-aware execution can boost LLM agent accuracy by over 2% in long-horizon tasks, revealing a critical leverage point for enhancing agent stability.
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.
