Xun Zhou

9

Papers

69

Total Citations

Papers (9)

Over-Tokenized Transformer: Vocabulary is Generally Worth Scaling

Hyper-Connections

Design Principle Transfer in Neural Architecture Search via Large Language Models

Polynomial Composition Activations: Unleashing the Dynamics of Large Language Models

GeoPro-Net: Learning Interpretable Spatiotemporal Prediction Models Through Statistically-Guided Geo-Prototyping

FT-GAN: Fine-Grained Tune Modeling for Chinese Opera Synthesis

Faster Online Learning of Optimal Threshold for Consistent F-measure Optimization

ProtoX: Explaining a Reinforcement Learning Agent via Prototyping

SpatialRank: Urban Event Ranking with NDCG Optimization on Spatiotemporal Data