5 papers
DUD: Decoupled Update Dynamics for Reliable Uncertainty Quantification in Large Language Models
Yixin Bu, Runze Xia, Guanyun Zou +3
Accurate Uncertainty Quantification (UQ) is critical for reliable deployment of Large Language Models (LLMs), yet traditional probability-based metrics often fail to capture the mo…
Hallucination Mitigating for Medical Report Generation
Ruoqing Zhao, Runze Xia, Piji Li
In the realm of medical report generation (MRG), the integration of natural language processing has emerged as a vital tool to alleviate the workload of radiologists. Despite the i…
From Reasoning LLMs to BERT: A Two-Stage Distillation Framework for Search Relevance
Runze Xia, Yupeng Ji, Yuxi Zhou +3
Query-service relevance prediction in e-commerce search systems faces strict latency requirements that prevent the direct application of Large Language Models (LLMs). To bridge thi…
Improving Brain-to-Image Reconstruction via Fine-Grained Text Bridging
Runze Xia, Shuo Feng, Renzhi Wang +3
Brain-to-Image reconstruction aims to recover visual stimuli perceived by humans from brain activity. However, the reconstructed visual stimuli often missing details and semantic i…
Decoding the Echoes of Vision from fMRI: Memory Disentangling for Past Semantic Information
Runze Xia, Congchi Yin, Piji Li
The human visual system is capable of processing continuous streams of visual information, but how the brain encodes and retrieves recent visual memories during continuous visual p…