HiMoE: Heterogeneity-Informed Mixture-of-Experts for Fair Spatial-Temporal Forecastingby Shaohan Yu, Pan Deng, Yu Zhao, Junting Liu,…
Condense, Don’t Just Prune: Enhancing Efficiency and Performance in MoE Layer Pruningby Mingyu Cao, Gen…
Mixture of Cache-Conditional Experts for Efficient Mobile Device Inferenceby Andrii Skliar, Ties van Rozendaal, Romain…
On the effectiveness of discrete representations in sparse mixture of expertsby Giang Do, Kha Pham,…
Mixture of Experts in Image Classification: What’s the Sweet Spot?by Mathurin Videau, Alessandro Leite, Marc…
LDACP: Long-Delayed Ad Conversions Prediction Model for Bidding Strategyby Peng Cui, Yiming Yang, Fusheng Jin,…
Ultra-Sparse Memory Networkby Zihao Huang, Qiyang Min, Hongzhi Huang, Defa Zhu, Yutao Zeng, Ran Guo,…
Weakly-Supervised Multimodal Learning on MIMIC-CXRby Andrea Agostini, Daphné Chopard, Yang Meng, Norbert Fortin, Babak Shahbaba,…
Sparse Upcycling: Inference Inefficient Finetuningby Sasha Doubov, Nikhil Sardana, Vitaliy ChileyFirst submitted to arxiv on:…
Lynx: Enabling Efficient MoE Inference through Dynamic Batch-Aware Expert Selectionby Vima Gupta, Kartik Sinha, Ada…