LY Corporation R&D

Our papers have been accepted at Forty-Third International Conference on Machine Learning (ICML 2026)(external link)

Shuffling-Aware Optimization for Private Vector Mean Estimation
Shun Takagi, Seng Pei Liew

Inference-Aware Meta-Alignment of LLMs via Non-Linear GRPO
Shokichi Takakura, Akifumi Wachi, Rei Higuchi (The University of Tokyo/RIKEN AIP), Kohei Miyaguchi, Taiji Suzuki (The University of Tokyo/RIKEN AIP)

Tighter Regret Lower Bound for Gaussian Process Bandits with Squared Exponential Kernel in Hypersphere
Shogo Iwazaki

Local Hessian Spectral Filtering for Robust Intrinsic Dimension Estimation
Genki Osada