SepsisLab: Early Sepsis Prediction with Uncertainty Quantification and Active Sensingby Changchang Yin, Pin-Yu Chen, Bingsheng…
Towards Robust Knowledge Tracing Models via k-Sparse Attentionby Shuyan Huang, Zitao Liu, Xiangyu Zhao, Weiqi…
Wonderful Matrices: More Efficient and Effective Architecture for Language Modeling Tasksby Jingze Shi, Bingheng Wu,…
Masked Graph Learning with Recurrent Alignment for Multimodal Emotion Recognition in Conversationby Tao Meng, Fuchen…
Forecasting Automotive Supply Chain Shortfalls with Heterogeneous Time Seriesby Bach Viet Do, Xingyu Li, Chaoye…
Diffusion Transformer Captures Spatial-Temporal Dependencies: A Theory for Gaussian Process Databy Hengyu Fu, Zehao Dou,…
On the Benefits of Rank in Attention Layersby Noah Amsel, Gilad Yehudai, Joan BrunaFirst submitted…
RazorAttention: Efficient KV Cache Compression Through Retrieval Headsby Hanlin Tang, Yang Lin, Jing Lin, Qingsen…
CRMSP: A Semi-supervised Approach for Key Information Extraction with Class-Rebalancing and Merged Semantic Pseudo-Labelingby Qi…
Attention Is All You Need But You Don’t Need All Of It For Inference of…