Scaling Laws for Vision-Language Fusionwith Seng Pei Liew, Teppei Suzuki1 versionW_5vxu95wgv1 · current
When Does Metadata Conditioning (NOT) Work for Language Model Pre-Training? A Study with Context-Free GrammarsRei Higuchi, Ryotaro Kawata, Naoki Nishikawa et al.0 citations2504.17562v22025arXiv
Disentanglement Analysis with Partial Information DecompositionSeiya Tokui, Issei Sato2 citations2108.13753v22021arXiv
Chainer: A Deep Learning Framework for Accelerating the Research CycleSeiya Tokui, Ryosuke Okuta, Takuya Akiba et al.26 citations1908.00213v12019arXiv
Adversarial Attacks and Defences CompetitionAlexey Kurakin, Ian Goodfellow, Samy Bengio et al.314 citations1804.00097v12018arXiv
Learning Discrete Representations via Information Maximizing Self-Augmented TrainingWeihua Hu, Takeru Miyato, Seiya Tokui et al.364 citations1702.08720v32017arXiv
Reparameterization trick for discrete variablesSeiya Tokui, Issei sato7 citations1611.01239v12016arXiv