Suzuki, Jun

11 publications

ICLR 2025 Drop-Upcycling: Training Sparse Mixture of Experts with Partial Re-Initialization Taishi Nakamura, Takuya Akiba, Kazuki Fujii, Yusuke Oda, Rio Yokota, Jun Suzuki

NeurIPS 2025 Transformer Key-Value Memories Are Nearly as Interpretable as Sparse Autoencoders Mengyu Ye, Jun Suzuki, Tatsuro Inaba, Tatsuki Kuribayashi

CVPR 2025 VDocRAG: Retrieval-Augmented Generation over Visually-Rich Documents Ryota Tanaka, Taichi Iki, Taku Hasegawa, Kyosuke Nishida, Kuniko Saito, Jun Suzuki

AAAI 2024 InstructDoc: A Dataset for Zero-Shot Generalization of Visual Document Understanding with Instructions Ryota Tanaka, Taichi Iki, Kyosuke Nishida, Kuniko Saito, Jun Suzuki

AAAI 2019 Character N-Gram Embeddings to Improve RNN Language Models Sho Takase, Jun Suzuki, Masaaki Nagata

AAAI 2019 Mixture of Expert/Imitator Networks: Scalable Semi-Supervised Learning Framework Shun Kiyono, Jun Suzuki, Kentaro Inui

IJCAI 2018 Interpretable Adversarial Perturbation in Input Embedding Space for Text Motoki Sato, Jun Suzuki, Hiroyuki Shindo, Yuji Matsumoto

IJCAI 2016 Learning Compact Neural Word Embeddings by Parameter Space Sharing Jun Suzuki, Masaaki Nagata

AAAI 2014 Fused Feature Representation Discovery for High-Dimensional and Sparse Data Jun Suzuki, Masaaki Nagata

NeurIPS 2005 Sequence and Tree Kernels with Statistical Feature Mining Jun Suzuki, Hideki Isozaki

NeurIPS 2003 Kernels for Structured Natural Language Data Jun Suzuki, Yutaka Sasaki, Eisaku Maeda