Kirato Yoshihara

Gradient Descent towards a big impact.

News ·

Awarded the Nakajima Foundation Fellowship.

A fellowship for graduate study abroad, awarded to approximately 10 recipients annually (typically 2–3 in computer science).

Looking for PhD opportunities in EE/CS in the US for Fall 2027.

About

Hi there! I'm Kirato — a builder with research at heart, currently a final-year undergrad at The University of Osaka. Now at MBZUAI and AIST, previously at Preferred Networks.

Research Interests

Foundation Models, Efficient Learning, Representation Learning

Publications

VesselBridge3D: A Foundation Model Adaptation Framework for Label-Efficient 3D Vessel Segmentation

Kirato Yoshihara, Yohei Sugawara, Yuta Tokuoka, Lihang Hong
SWITCH+ Workshop @ MICCAI 2026 · Spotlight

Modular Norm RandOpt: Population-Efficient Ensembling through Architecture-Aware Perturbations

Kirato Yoshihara, Hiroaki Hamade
Under review at ICLR 2027・Accepted at NeurReps @ NeurIPS 2026

Curriculum Vitae

Essays

A ligand in a blue protein binding pocket
9/8 2026

Verifiable Docking: Repairing Only What Needs to Move

A docking pose can be almost right and still clash with the protein. Can the clash itself tell us what to repair?
Surface normal visualization for Rethinking 0x5F3759DF for GPUs
5/13 2026

Rethinking 0x5F3759DF for GPUs

The old spell was 0x5F3759DF. We recast it for GPUs, FP16/BF16, and RMSNorm, and discovered that modern magic may need a lookup table.
Assignments of different layers to different manifolds
4/17 2026

Different Layers, Different Manifolds: Scaling Manifold Muon to GPT-2

Manifold Muon constrains weights to have nice spectral properties. But which manifold should each layer live on? We tried five assignments on GPT-2 and only three survived.

Fun Facts about Me

Mac or Windows?
Mac
Coffee or tea?
Coffee
City or nature?
Nature — a.k.a. Nagano
Favorite editor?
Codex
Best model weights?
model_final_v4_actually_best_20260409_0342_newer_important.pth