2 citations · 2 across the 8 of their papers we have counts for
Showing cs.LGShow all
3 papers · 1 filter
cs.LG2026
Even GPT-5.2 Can't Count to Five: The Case for Zero-Error Horizons in Trustworthy LLMs
Ryoma Sato
We propose Zero-Error Horizon (ZEH) for trustworthy LLMs, which represents the maximum range that a model can solve without any errors. While ZEH itself is simple, we demonstrate t…
cs.LG2025
Interestingness First Classifiers
Ryoma Sato
Most machine learning models are designed to maximize predictive accuracy. In this work, we explore a different goal: building classifiers that are interesting. An ``interesting cl…
cs.LG2024
Training-free Graph Neural Networks and the Power of Labels as Features
Ryoma Sato
We propose training-free graph neural networks (TFGNNs), which can be used without training and can also be improved with optional training, for transductive node classification. W…