ProSparse: Introducing and Enhancing Intrinsic Activation Sparsity within Large Language Modelsby Chenyang Song, Xu Han,…
ToDo: Token Downsampling for Efficient Generation of High-Resolution Imagesby Ethan Smith, Nayan Saxena, Aninda SahaFirst…
Transformer tricks: Precomputing the first layerby Nils GraefFirst submitted to arxiv on: 20 Feb 2024CategoriesMain:…
Bayesian Neural Networks with Domain Knowledge Priorsby Dylan Sam, Rattana Pukdee, Daniel P. Jeong, Yewon…
Efficiently Predicting Mutational Effect on Homologous Proteins by Evolution Encodingby Zhiqiang Zhong, Davide MottinFirst submitted…
LinkSAGE: Optimizing Job Matching Using Graph Neural Networksby Ping Liu, Haichao Wei, Xiaochen Hou, Jianqiang…
SMORE: Similarity-based Hyperdimensional Domain Adaptation for Multi-Sensor Time Series Classificationby Junyao Wang, Mohammad Abdullah Al…
Causal hybrid modeling with double machine learningby Kai-Hendrik Cohrs, Gherardo Varando, Nuno Carvalhais, Markus Reichstein,…
Improving Neural-based Classification with Logical Background Knowledgeby Arthur Ledaguenel, Céline Hudelot, Mostepha KhouadjiaFirst submitted to…
Identifying Factual Inconsistencies in Summaries: Grounding LLM Inference via Task Taxonomyby Liyan Xu, Zhenlin Su,…