Multi-Branch Transformerwith Gaotang Li, Lingjie Chen, Zhiwei Xu, Hongzheng Chen +41 versionW_ptgss8npv1 · current
LT2: Linear-Time Looped TransformersChunyuan Deng, Yizhe Zhang, Rui-Jie Zhu et al.0 citations2605.20670v22026arXiv
ByteFlow: Language Modeling through Adaptive Byte Compression without a TokenizerChunyuan Deng, Sanket Lokegaonkar, Colin Lockard et al.0 citations2603.03583v12026arXiv
Spherical Steering: Geometry-Aware Activation Rotation for Language ModelsZejia You, Chunyuan Deng, Hanjie Chen0 citations2602.08169v22026arXiv
Steering Information Utility in Key-Value Memory for Language Model Post-TrainingChunyuan Deng, Ruidi Chang, Hanjie Chen0 citations2507.05158v22025arXiv