activity
20232025
most citedUnderstanding Diffusion Models by Feynman's Path Integral

1 citations · 1 across the 1 of their papers we have counts for

collaborators

6 papers

hep-th2025

Self-similar inverse cascade from generalized symmetries

Yuji Hirono, Kohei Kamada, Naoki Yamamoto +1

We investigate the role of generalized symmetries in driving non-equilibrium and non-linear phenomena, specifically focusing on turbulent systems. While conventional turbulence stu…

cond-mat.soft2024

Data-driven discovery of self-similarity using neural networks

Ryota Watanabe, Takanori Ishii, Yuji Hirono +1

Finding self-similarity is a key step for understanding the governing law behind complex physical phenomena. Traditional methods for identifying self-similarity often rely on speci…

hep-th2024

Neural network representation of quantum systems

Koji Hashimoto, Yuji Hirono, Jun Maeda +1

It has been proposed that random wide neural networks near Gaussian process are quantum field theories around Gaussian fixed points. In this paper, we provide a novel map with whic…

cs.LG20241 cited

Understanding Diffusion Models by Feynman's Path Integral

Yuji Hirono, Akinori Tanaka, Kenji Fukushima

Score-based diffusion models have proven effective in image generation and have gained widespread usage; however, the underlying factors contributing to the performance disparity b…

cs.LG2024

Unification of Symmetries Inside Neural Networks: Transformer, Feedforward and Neural ODE

Koji Hashimoto, Yuji Hirono, Akiyoshi Sannai

Understanding the inner workings of neural networks, including transformers, remains one of the most challenging puzzles in machine learning. This study introduces a novel approach…

hep-ph2023

Quarkonium spectral functions in a bulk-viscous quark-gluon plasma

Lata Thakur, Yuji Hirono

We study the interplay of non-equilibrium properties of a quark-gluon plasma (QGP) and heavy quarkonia. For this purpose, we compute the quarkonium spectral functions in a bulk-vis…