Kraken: Inherently Parallel Transformers For Efficient Multi-Device Inferenceby Rohan Baskar Prabhakar, Hengrui Zhang, David WentzlaffFirst…
Multi-task Heterogeneous Graph Learning on Electronic Health Recordsby Tsai Hor Chan, Guosheng Yin, Kyongtae Bae,…
Model Based and Physics Informed Deep Learning Neural Network Structuresby Ali Mohammad-Djafari, Ning Chu, Li…
Post-Training Sparse Attention with Double Sparsityby Shuo Yang, Ying Sheng, Joseph E. Gonzalez, Ion Stoica,…
Variational Learning of Gaussian Process Latent Variable Models through Stochastic Gradient Annealed Importance Samplingby Jian…
Value of Information and Reward Specification in Active Inference and POMDPsby Ran WeiFirst submitted to…
Divide-and-Conquer Predictive Coding: a structured Bayesian inference algorithmby Eli Sennesh, Hao Wu, Tommaso SalvatoriFirst submitted…
Sampling Foundational Transformer: A Theoretical Perspectiveby Viet Anh Nguyen, Minh Lenhat, Khoa Nguyen, Duong Duc…
Speculative Diffusion Decoding: Accelerating Language Generation through Diffusionby Jacob K Christopher, Brian R Bartoldson, Tal…
Eigen Attention: Attention in Low-Rank Space for KV Cache Compressionby Utkarsh Saxena, Gobinda Saha, Sakshi…