Graph Neural Networks for Quantifying Compatibility Mechanisms in Traditional Chinese Medicineby Jingqi Zeng, Xiaobin JiaFirst…
TabDeco: A Comprehensive Contrastive Framework for Decoupled Representations in Tabular Databy Suiyao Chen, Jing Wu,…
AMAGO-2: Breaking the Multi-Task Barrier in Meta-Reinforcement Learning with Transformersby Jake Grigsby, Justin Sasek, Samyak…
Distributed solar generation forecasting using attention-based deep neural networks for cloud movement predictionby Maneesha Perera,…
SageAttention2: Efficient Attention with Thorough Outlier Smoothing and Per-thread INT4 Quantizationby Jintao Zhang, Haofeng Huang,…
An Investigation of Offline Reinforcement Learning in Factorisable Action Spacesby Alex Beeson, David Ireland, Giovanni…
MetaLA: Unified Optimal Linear Approximation to Softmax Attention Mapby Yuhong Chou, Man Yao, Kexin Wang,…
One-Layer Transformer Provably Learns One-Nearest Neighbor In Contextby Zihao Li, Yuan Cao, Cheng Gao, Yihan…
Challenges in the Differential Classification of Individual Diagnoses from Co-Occurring Autism and ADHD Using Survey…
SmoothCache: A Universal Inference Acceleration Technique for Diffusion Transformersby Joseph Liu, Joshua Geddes, Ziyu Guo,…