Jiayi Xin

Paraphrase-Robust Conformal Prediction for Reliable LLM Uncertainty Quantification

Modalities Contribute Unequally: Enhancing Medical Multi-modal Learning through Adaptive Modality Token Re-balancing

$I$^2$MoE$: Interpretable Multimodal Interaction-aware Mixture-of-Experts

Sparse MoE as a New Retriever: Addressing Missing Modality Problem in Incomplete Multimodal Data

Multimodal Graph-LLM: Leveraging Graph-Enhanced LLMs for Multimodal Healthcare Predictions