Výsledky vyhledávání

Report

ADOPT: Modified Adam Can Converge with Any $\beta_2$ with the Optimal Rate

Autor: Taniguchi, Shohei, Harada, Keno, Minegishi, Gouki, Oshima, Yuta, Jeong, Seong Cheol, Nagahara, Go, Iiyama, Tomoshi, Suzuki, Masahiro, Iwasawa, Yusuke, Matsuo, Yutaka

Adam is one of the most popular optimization algorithms in deep learning. However, it is known that Adam does not converge in theory unless choosing a hyperparameter, i.e., $\beta_2$, in a problem-dependent manner. There have been many attempts to fi

Externí odkaz: http://arxiv.org/abs/2411.02853

Zobrazit plný text záznamu

Report

Enhancing Unimodal Latent Representations in Multimodal VAEs through Iterative Amortized Inference

Autor: Oshima, Yuta, Suzuki, Masahiro, Matsuo, Yutaka

Multimodal variational autoencoders (VAEs) aim to capture shared latent representations by integrating information from different data modalities. A significant challenge is accurately inferring representations from any subset of modalities without t

Externí odkaz: http://arxiv.org/abs/2410.11403

Zobrazit plný text záznamu

Report

SSM Meets Video Diffusion Models: Efficient Long-Term Video Generation with Structured State Spaces

Autor: Oshima, Yuta, Taniguchi, Shohei, Suzuki, Masahiro, Matsuo, Yutaka

Given the remarkable achievements in image generation through diffusion models, the research community has shown increasing interest in extending these models to video generation. Recent diffusion models for video generation have predominantly utiliz

Externí odkaz: http://arxiv.org/abs/2403.07711

Zobrazit plný text záznamu