5 papers
Rethinking Generative Recommender Tokenizer: Recsys-Native Encoding and Semantic Quantization Beyond LLMs
Yu Liang, Zhongjin Zhang, Yuxuan Zhu +10
Semantic ID (SID)-based recommendation is a promising paradigm for scaling sequential recommender systems, but existing methods largely follow a semantic-centric pipeline: item emb…
CheXLearner: Text-Guided Fine-Grained Representation Learning for Progression Detection
Yuanzhuo Wang, Junwen Duan, Xinyu Li +1
Temporal medical image analysis is essential for clinical decision-making, yet existing methods either align images and text at a coarse level - causing potential semantic mismatch…
DDO: Dual-Decision Optimization for LLM-Based Medical Consultation via Multi-Agent Collaboration
Zhihao Jia, Mingyi Jia, Junwen Duan +1
Large Language Models (LLMs) demonstrate strong generalization and reasoning abilities, making them well-suited for complex decision-making tasks such as medical consultation (MC).…
ICA-RAG: Information Completeness Guided Adaptive Retrieval-Augmented Generation for Disease Diagnosis
Jiawei He, Mingyi Jia, Zhihao Jia +3
Retrieval-Augmented Large Language Models (LLMs), which integrate external knowledge, have shown remarkable performance in medical domains, including clinical diagnosis. However, e…
MARE: Multi-Aspect Rationale Extractor on Unsupervised Rationale Extraction
Han Jiang, Junwen Duan, Zhe Qu +1
Unsupervised rationale extraction aims to extract text snippets to support model predictions without explicit rationale annotation. Researchers have made many efforts to solve this…