Masahiro Suzuki

33 papers A* 3Journal 25Unranked 5

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Enhancing Unimodal Latent Representations in Multimodal VAEs Through Iterative Amortized Inference. New Gener. Comput. Yuta Oshima, Masahiro Suzuki, Yutaka Matsuo
2025	J	`jnl`	Efficient Object-Centric Representation Learning using Masked Generative Modeling. Trans. Mach. Learn. Res. Akihiro Nakano, Masahiro Suzuki, Yutaka Matsuo
2025	J	`jnl`	How Semantically Informative is an Image?: Measuring the Covariance-Weighted Norm of Contrastive Learning Embeddings. CoRR Fumiya Uchiyama, Rintaro Yanagi, Shohei Taniguchi, Shota Takashiro, Masahiro Suzuki, Hirokatsu Kataoka, Yusuke Iwasawa, Yutaka Matsuo
2025	J	`jnl`	Inference-Time Text-to-Video Alignment with Diffusion Latent Beam Search. CoRR Yuta Oshima, Masahiro Suzuki, Yutaka Matsuo, Hiroki Furuta
2025	J	`jnl`	MultiBanana: A Challenging Benchmark for Multi-Reference Text-to-Image Generation. CoRR Yuta Oshima, Daiki Miyake, Kohsei Matsutani, Yusuke Iwasawa, Masahiro Suzuki, Yutaka Matsuo, Hiroki Furuta
2025	J	`jnl`	The Geometry of Phase Transitions in Diffusion Models: Tubular Neighbourhoods and Singularities. Trans. Mach. Learn. Res. Manato Yaguchi, Kotaro Sakamoto, Ryosuke Sakamoto, Masato Tanabe, Masatomo Akagawa, Yusuke Hayashi, Masahiro Suzuki, Yutaka Matsuo
2025	J	`jnl`	When Object-Centric World Models Meet Policy Learning: From Pixels to Policies, and Where It Breaks. CoRR Stefano Ferraro, Akihiro Nakano, Masahiro Suzuki, Yutaka Matsuo
2025	J	`jnl`	WorldPack: Compressed Memory Improves Spatial Consistency in Video World Modeling. CoRR Yuta Oshima, Yusuke Iwasawa, Masahiro Suzuki, Yutaka Matsuo, Hiroki Furuta
2024	A*	`conf`	ADOPT: Modified Adam Can Converge with Any β NeurIPS Shohei Taniguchi, Keno Harada, Gouki Minegishi, Yuta Oshima, Seong Cheol Jeong, Go Nagahara, Tomoshi Iiyama, Masahiro Suzuki, Yusuke Iwasawa, Yutaka Matsuo
2024	J	`jnl`	ADOPT: Modified Adam Can Converge with Any β CoRR Shohei Taniguchi, Keno Harada, Gouki Minegishi, Yuta Oshima, Seong Cheol Jeong, Go Nagahara, Tomoshi Iiyama, Masahiro Suzuki, Yusuke Iwasawa, Yutaka Matsuo
2024	J	`jnl`	Enhancing Unimodal Latent Representations in Multimodal VAEs through Iterative Amortized Inference. CoRR Yuta Oshima, Masahiro Suzuki, Yutaka Matsuo
2024	J	`jnl`	Object-Centric Temporal Consistency via Conditional Autoregressive Inductive Biases. CoRR Cristian Meo, Akihiro Nakano, Mircea Lica, Aniket Didolkar, Masahiro Suzuki, Anirudh Goyal, Mengmi Zhang, Justin Dauwels, Yutaka Matsuo, Yoshua Bengio
2024	J	`jnl`	SSM Meets Video Diffusion Models: Efficient Video Generation with Structured State Spaces. CoRR Yuta Oshima, Shohei Taniguchi, Masahiro Suzuki, Yutaka Matsuo
2024	J	`jnl`	The Embodied World Model Based on LLM with Visual Information and Prediction-Oriented Prompts. CoRR Wakana Haijima, Kou Nakakubo, Masahiro Suzuki, Yutaka Matsuo
2024	—	`conf`	The Geometry of Diffusion Models: Tubular Neighbourhoods and Singularities. GRaM Kotaro Sakamoto, Ryosuke Sakamoto, Masato Tanabe, Masatomo Akagawa, Yusuke Hayashi, Manato Yaguchi, Masahiro Suzuki, Yutaka Matsuo
2023	A*	`conf`	End-to-end Training of Deep Boltzmann Machines by Unbiased Contrastive Divergence with Local Mode Initialization. ICML Shohei Taniguchi, Masahiro Suzuki, Yusuke Iwasawa, Yutaka Matsuo
2023	J	`jnl`	End-to-end Training of Deep Boltzmann Machines by Unbiased Contrastive Divergence with Local Mode Initialization. CoRR Shohei Taniguchi, Masahiro Suzuki, Yusuke Iwasawa, Yutaka Matsuo
2023	J	`jnl`	HAWK-Net: Hierarchical Attention Weighted Top-K Network for High-resolution Image Classification. J. Inf. Process. Hitoshi Nakanishi, Masahiro Suzuki, Yutaka Matsuo
2023	—	`conf`	Improving the Robustness to Variations of Objects and Instructions with a Neuro-Symbolic Approach for Interactive Instruction Following. MMM (2) Kazutoshi Shinoda, Yuki Takezawa, Masahiro Suzuki, Yusuke Iwasawa, Yutaka Matsuo
2023	A*	`conf`	Interaction-Based Disentanglement of Entities for Object-Centric World Models. ICLR Akihiro Nakano, Masahiro Suzuki, Yutaka Matsuo
2023	J	`jnl`	Learning global spatial information for multi-view object-centric models. Adv. Robotics Yuya Kobayashi, Masahiro Suzuki, Yutaka Matsuo
2023	J	`jnl`	Pixyz: a Python library for developing deep generative models. Adv. Robotics Masahiro Suzuki, Takaaki Kaneko, Yutaka Matsuo
2022	J	`jnl`	A survey of multimodal deep generative models. Adv. Robotics Masahiro Suzuki, Yutaka Matsuo
2022	J	`jnl`	A survey of multimodal deep generative models. CoRR Masahiro Suzuki, Yutaka Matsuo
2022	J	`jnl`	Fixing the Train-test Objective Discrepancy: Iterative Image Inpainting for Unsupervised Anomaly Detection. J. Inf. Process. Hitoshi Nakanishi, Masahiro Suzuki, Yutaka Matsuo
2021	J	`jnl`	Improving the Robustness to Variations of Objects and Instructions with a Neuro-Symbolic Approach for Interactive Instruction Following. CoRR Kazutoshi Shinoda, Yuki Takezawa, Masahiro Suzuki, Yusuke Iwasawa, Yutaka Matsuo
2021	J	`jnl`	Pixyz: a library for developing deep generative models. CoRR Masahiro Suzuki, Takaaki Kaneko, Yutaka Matsuo
2019	—	`conf`	Dual Space Learning with variational Autoencoders. DGS@ICLR Hirono Okamoto, Masahiro Suzuki, Itto Higuchi, Shohei Ohsawa, Yutaka Matsuo
2019	—	`conf`	UVTON: UV Mapping to Consider the 3D Structure of a Human in Image-Based Virtual Try-On Network. ICCV Workshops Shizuma Kubo, Yusuke Iwasawa, Masahiro Suzuki, Yutaka Matsuo
2018	J	`jnl`	Improving Bi-directional Generation between Different Modalities with Variational Autoencoders. CoRR Masahiro Suzuki, Kotaro Nakayama, Yutaka Matsuo
2017	—	`conf`	Joint Multimodal Learning with Deep Generative Models. ICLR (Workshop) Masahiro Suzuki, Kotaro Nakayama, Yutaka Matsuo
2016	J	`jnl`	Joint Multimodal Learning with Deep Generative Models. CoRR Masahiro Suzuki, Kotaro Nakayama, Yutaka Matsuo
2016	J	`jnl`	Neural Machine Translation with Latent Semantic of Image and Text. CoRR Joji Toyama, Masanori Misono, Masahiro Suzuki, Kotaro Nakayama, Yutaka Matsuo