Variational Pseudo Marginal Methods for Jet Reconstruction in Particle Physicsby Hanming Yang, Antonio Khalil Moretti,…
Enhancing the Resilience of Graph Neural Networks to Topological Perturbations in Sparse Graphsby Shuqi He,…
Efficient User Sequence Learning for Online Services via Compressed Graph Neural Networksby Yucheng Wu, Liyue…
Improved context-sensitive transformer model for inland vessel trajectory predictionby Kathrin Donandt, Karim Böttger, Dirk SöffkerFirst…
You Only Accept Samples Once: Fast, Self-Correcting Stochastic Variational Inferenceby Dominic B. DaytaFirst submitted to…
Exploring Effects of Hyperdimensional Vectors for Tsetlin Machinesby Vojtech Halenka, Ahmed K. Kadhim, Paul F.…
Block Transformer: Global-to-Local Language Modeling for Fast Inferenceby Namgyu Ho, Sangmin Bae, Taehyeon Kim, Hyunjik…
Adaptive Layer Splitting for Wireless LLM Inference in Edge Computing: A Model-Based Reinforcement Learning Approachby…
Progressive Inference: Explaining Decoder-Only Sequence Classification Models Using Intermediate Predictionsby Sanjay Kariyappa, Freddy Lécué, Saumitra…
Loki: Low-rank Keys for Efficient Sparse Attentionby Prajwal Singhania, Siddharth Singh, Shwai He, Soheil Feizi,…