Contrastive Learning on Medical Intents for Sequential Prescription Recommendationby Arya Hadizadeh Moghaddam, Mohsen Nayebi Kerdabadi,…
OpenCity: Open Spatio-Temporal Foundation Models for Traffic Predictionby Zhonghang Li, Long Xia, Lei Shi, Yong…
Increasing transformer token length with a Maximum Entropy Principle Methodby R. I. CukierFirst submitted to…
PLUTUS: A Well Pre-trained Large Unified Transformer can Unveil Financial Time Series Regularitiesby Yuanjian Xu,…
Transformers to SSMs: Distilling Quadratic Knowledge to Subquadratic Modelsby Aviv Bick, Kevin Y. Li, Eric…
ShortCircuit: AlphaZero-Driven Circuit Designby Dimitrios Tsaras, Antoine Grosnit, Lei Chen, Zhiyao Xie, Haitham Bou-Ammar, Mingxuan…
Instruction-Based Molecular Graph Generation with Unified Text-Graph Diffusion Modelby Yuran Xiang, Haiteng Zhao, Chang Ma,…
MoDeGPT: Modular Decomposition for Large Language Model Compressionby Chi-Heng Lin, Shangqian Gao, James Seale Smith,…
Attention is a smoothed cubic splineby Zehua Lai, Lek-Heng Lim, Yucong LiuFirst submitted to arxiv…
LightWeather: Harnessing Absolute Positional Encoding to Efficient and Scalable Global Weather Forecastingby Yisong Fu, Fei…