8 papers
CONSISTRE: A Unified Consistency-Aware Framework for Document-Level Relation Extraction with Large Language Models
Mingxuan Sun
Document-level relation extraction (DocRE) aims to extract relations among multiple entities across extended contexts while maintaining consistency across predicted triples. Althou…
FLEX-MoE: Federated Mixture-of-Experts with Load-balanced Expert Assignment for Edge Computing
Boyang Zhang, Xiaobing Chen, Songyang Zhang +4
Mixture-of-Experts (MoE) models enable scalable neural networks through conditional computation, offering enhanced effectiveness and efficiency for next-generation wireless communi…
Spatiotemporal-Aware Bit-Flip Injection on DNN-based Advanced Driver Assistance Systems (extended version)
Taibiao Zhao, Xiang Zhang, Mingxuan Sun +2
Modern advanced driver assistance systems (ADAS) rely on deep neural networks (DNNs) for perception and planning. Since DNNs' parameters reside in DRAM during inference, bit flips…
Learning to Rank with Top- Fairness
Boyang Zhang, Quanqi Hu, Mingxuan Sun +2
Fairness in ranking models is crucial, as disparities in exposure can disproportionately affect protected groups. Most fairness-aware ranking systems focus on ensuring comparable a…
Pruning and Malicious Injection: A Retraining-Free Backdoor Attack on Transformer Models
Taibiao Zhao, Mingxuan Sun, Hao Wang +2
Transformer models have demonstrated exceptional performance and have become indispensable in computer vision (CV) and natural language processing (NLP) tasks. However, recent stud…
Enhancing Time Series Forecasting via Multi-Level Text Alignment with LLMs
Taibiao Zhao, Xiaobing Chen, Mingxuan Sun
The adaptation of large language models (LLMs) to time series forecasting poses unique challenges, as time series data is continuous in nature, while LLMs operate on discrete token…