Author

Akiyoshi Tomihari

h-index 3 View on Semantic Scholar

We have 2 of 5 papers

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.

#artificial intelligence Preprint Sep 2026

LLM-as-an-Improver: Turning Verification into Better Candidates

LLM-as-an-Improver is introduced and Verify--Repair--Reselect (VRR) is proposed, which uses verification feedback to generate and reselect improved candidates and highlights a broader role for LLMs as improvers: verification feedback can not only select among existing solutions but also construct stronger candidates be...

Akiyoshi Tomihari, Yuma Ichikawa · 0 citations

#artificial intelligence Preprint Jan 2025

Gradient Heterogeneity Complements Hessian Heterogeneity in Transformer Optimization

This study provides a theoretical analysis showing that gradient heterogeneity, together with Hessian heterogeneity, degrades the convergence of gradient-based methods such as SGD, while sign-based methods are substantially less sensitive to this effect.

Akiyoshi Tomihari, Issei Sato · 6 citations · ⚡1