8 papers
MGDT: MLLM-Guided Diffusion Transformer with Relation-Adaptive Mixture-of-Experts for Multimodal Knowledge Graph Completion
Xu Hou, Meiyu Liang, Wei Huang +6
Multimodal Knowledge Graph Completion (MKGC) requires inferring missing entities from structural, textual, and visual cues. Existing diffusion-based MKGC methods usually denoise di…
What Does Your Short-Answer VQA Score Actually Measure? Evaluator-Dependent Instability in Multimodal Short-Answer Benchmarks
Guanhua Ye, Niu Jingbin, Yan Li +4
Short-answer VQA benchmarks conflate two distinct quantities: whether a model's answer is semantically correct, and whether that answer matches the surface form expected by the aut…
Beyond Metadata: CAPRA for Hidden Subgroup Analysis under Missing Metadata in Medical Imaging
Yawen Li, Yan Li, Zhe Xue +3
Medical imaging models are often deployed without the demographic, acquisition, and quality metadata needed for subgroup auditing. Once those metadata disappear, clinically critica…
Trust-free Personalized Decentralized Learning
Yawen Li, Yan Li, Junping Du +3
Personalized collaborative learning in federated settings faces a critical trade-off between customization and participant trust. Existing approaches typically rely on centralized…
ELMM: Efficient Lightweight Multimodal Large Language Models for Multimodal Knowledge Graph Completion
Wei Huang, Peining Li, Meiyu Liang +7
Multimodal Knowledge Graphs (MKGs) extend traditional knowledge graphs by incorporating visual and textual modalities, enabling richer and more expressive entity representations. H…
DiffusionCom: Structure-Aware Multimodal Diffusion Model for Multimodal Knowledge Graph Completion
Wei Huang, Meiyu Liang, Peining Li +5
Most current MKGC approaches are predominantly based on discriminative models that maximize conditional likelihood. These approaches struggle to efficiently capture the complex con…