Summary of Artificial Intelligence For Science: the Easy and Hard Problems, by Ruairidh M. Battleday and Samuel J. Gershman
Artificial intelligence for science: The easy and hard problemsby Ruairidh M. Battleday, Samuel J. GershmanFirst…
Artificial intelligence for science: The easy and hard problemsby Ruairidh M. Battleday, Samuel J. GershmanFirst…
Unveiling the Statistical Foundations of Chain-of-Thought Prompting Methodsby Xinyang Hu, Fengzhuo Zhang, Siyu Chen, Zhuoran…
LLMs as Zero-shot Graph Learners: Alignment of GNN Representations with LLM Token Embeddingsby Duo Wang,…
Variational autoencoder-based neural network model compressionby Liang Cheng, Peiyuan Guan, Amir Taherkordi, Lei Liu, Dapeng…
A Multilateral Attention-enhanced Deep Neural Network for Disease Outbreak Forecasting: A Case Study on COVID-19by…
Improving Nonlinear Projection Heads using Pretrained Autoencoder Embeddingsby Andreas Schliebitz, Heiko Tapken, Martin AtzmuellerFirst submitted…
Estimating Uncertainty with Implicit Quantile Networkby Yi Hung LimFirst submitted to arxiv on: 26 Aug…
Retrieval Augmented Generation for Dynamic Graph Modelingby Yuxia Wu, Yuan Fang, Lizi LiaoFirst submitted to…
Towards Graph Prompt Learning: A Survey and Beyondby Qingqing Long, Yuchen Yan, Peiyan Zhang, Chen…
Adaptive Resolution Inference (ARI): Energy-Efficient Machine Learning for Internet of Thingsby Ziheng Wang, Pedro Reviriego,…