Author

Yusuke Mukuta

3 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#machine learning Preprint Oct 2026

The Implicit Bias of Hyperbolic Representation Learning for Multiclass Data: A Busemann Risk Perspective

We study the implicit bias of Riemannian gradient flow for hyperbolic multiclass classification with fixed class prototypes in hyperbolic space $\mathbb{H}^n$. Our framework accommodates general permutation invariant relative margin (PERM) losses, a class that includes cross entropy and other standard multiclass losses...

Xing-Run Li, Sho Kuno, Yusuke Mukuta et al. · 0 citations

#machine learning Preprint Sep 2026

$\mathbb{SL}(n)$ Representation Learning: An Intrinsic Mixed-Curvature Space with Higher Curvature Capacities and Deeper Order-Aware Composition

The $\mathbb{SL}(n)$ space is introduced, a representation geometry defined by the simple $\det(A)=1$ constraint and a left invariant Schatten-$p$ Finsler structure that consistently outperforms a broad range of representation manifold baselines across graph benchmarks at different scales.

Xing-Run Li, Yusuke Mukuta, Xin Yang et al. · 0 citations

#machine learning Preprint Sep 2026

Linear Fusion MultiDiffusion for Fast Training-Free Spherical Panorama Generation

LF-MultiDiffusion is proposed, a training-free panorama generation method that extends MultiDiffusion to support linear projections between target and reference image spaces and achieves better visual quality, text alignment, and panoramic consistency than the strongest training-free baseline, while providing a 15.36%...

Akio Hayakawa, Yusuke Mukuta, Tatsuya Harada · 0 citations