125 citations · 392 across the 13 of their papers we have counts for
16 papers
Inference-Time Text-to-Video Alignment with Diffusion Latent Beam Search
Yuta Oshima, Masahiro Suzuki, Yutaka Matsuo +1
The remarkable progress in text-to-video diffusion models enables the generation of photorealistic videos, although the content of these generated videos often includes unnatural m…
Enhancing Unimodal Latent Representations in Multimodal VAEs through Iterative Amortized Inference
Yuta Oshima, Masahiro Suzuki, Yutaka Matsuo
Multimodal variational autoencoders (VAEs) aim to capture shared latent representations by integrating information from different data modalities. A significant challenge is accura…
The Embodied World Model Based on LLM with Visual Information and Prediction-Oriented Prompts
Wakana Haijima, Kou Nakakubo, Masahiro Suzuki +1
In recent years, as machine learning, particularly for vision and language understanding, has been improved, research in embedded AI has also evolved. VOYAGER is a well-known LLM-b…
SSM Meets Video Diffusion Models: Efficient Long-Term Video Generation with Structured State Spaces
Yuta Oshima, Shohei Taniguchi, Masahiro Suzuki +1
Given the remarkable achievements in image generation through diffusion models, the research community has shown increasing interest in extending these models to video generation.…
End-to-end Training of Deep Boltzmann Machines by Unbiased Contrastive Divergence with Local Mode Initialization
Shohei Taniguchi, Masahiro Suzuki, Yusuke Iwasawa +1
We address the problem of biased gradient estimation in deep Boltzmann machines (DBMs). The existing method to obtain an unbiased estimator uses a maximal coupling based on a Gibbs…
World Models and Predictive Coding for Cognitive and Developmental Robotics: Frontiers and Challenges
Tadahiro Taniguchi, Shingo Murata, Masahiro Suzuki +8
Creating autonomous robots that can actively explore the environment, acquire knowledge and learn skills continuously is the ultimate achievement envisioned in cognitive and develo…
A survey of multimodal deep generative models
Masahiro Suzuki, Yutaka Matsuo
Multimodal learning is a framework for building models that make predictions based on different types of modalities. Important challenges in multimodal learning are the inference o…
Score Transformer: Generating Musical Score from Note-level Representation
Masahiro Suzuki
In this paper, we explore the tokenized representation of musical scores using the Transformer model to automatically generate musical scores. Thus far, sequence models have yielde…
Improving the Robustness to Variations of Objects and Instructions with a Neuro-Symbolic Approach for Interactive Instruction Following
Kazutoshi Shinoda, Yuki Takezawa, Masahiro Suzuki +2
An interactive instruction following task has been proposed as a benchmark for learning to map natural language instructions and first-person vision into sequences of actions to in…
Pixyz: a Python library for developing deep generative models
Masahiro Suzuki, Takaaki Kaneko, Yutaka Matsuo
With the recent rapid progress in the study of deep generative models (DGMs), there is a need for a framework that can implement them in a simple and generic way. In this research,…
A Whole Brain Probabilistic Generative Model: Toward Realizing Cognitive Architectures for Developmental Robots
Tadahiro Taniguchi, Hiroshi Yamakawa, Takayuki Nagai +5
Building a humanlike integrative artificial cognitive system, that is, an artificial general intelligence (AGI), is the holy grail of the artificial intelligence (AI) field. Furthe…
Neuro-SERKET: Development of Integrative Cognitive System through the Composition of Deep Probabilistic Generative Models
Tadahiro Taniguchi, Tomoaki Nakamura, Masahiro Suzuki +5
This paper describes a framework for the development of an integrative cognitive system based on probabilistic generative models (PGMs) called Neuro-SERKET. Neuro-SERKET is an exte…
Improving Bi-directional Generation between Different Modalities with Variational Autoencoders
Masahiro Suzuki, Kotaro Nakayama, Yutaka Matsuo
We investigate deep generative models that can exchange multiple modalities bi-directionally, e.g., generating images from corresponding texts and vice versa. A major approach to a…
Neural Machine Translation with Latent Semantic of Image and Text
Joji Toyama, Masanori Misono, Masahiro Suzuki +2
Although attention-based Neural Machine Translation have achieved great success, attention-mechanism cannot capture the entire meaning of the source sentence because the attention…
Generative Adversarial Nets from a Density Ratio Estimation Perspective
Masatoshi Uehara, Issei Sato, Masahiro Suzuki +2
Generative adversarial networks (GANs) are successful deep generative models. GANs are based on a two-player minimax game. However, the objective function derived in the original m…
Joint Multimodal Learning with Deep Generative Models
Masahiro Suzuki, Kotaro Nakayama, Yutaka Matsuo
We investigate deep generative models that can exchange multiple modalities bi-directionally, e.g., generating images from corresponding texts and vice versa. Recently, some studie…