collaborators

6 papers

cs.LG2026

Exact Fusion of Softmax Attention Heads Can Require Exponentially Many Atoms

Hiroyasu Usami, Keisuke Hara, Ayato Tsuboi +1

Fusing independently normalized attention heads can increase the number of explicit key-value entries, or atoms, needed to preserve their output. We prove a sharp separation for $W…

math.AP2026

Nonradial entire solutions of the critical Hénon equation for every

Phuong Le

We consider the critical Hénon equation in , . Gladiali, Grossi, and Neves (\emph{Advances in Mathematics}, 2013) constructed non…

cs.LG2026

Invertible Graph Aggregation Can Increase ReLU Readout Width

Hiroyasu Usami, Masanori Tsukamoto, Kohei Hashiguchi

An invertible graph aggregation preserves the complete feature table, but can increase the size of a classifier that reads one node at a time. For every even , we construct…

cs.DS2026

The Cost of Missed States: Online Tracking with Current-Observation Resets

Hiroyasu Usami

An online tracker retains one state and may reset only to the current observation, although its complete observed history is available. Offline knows the future and obeys the same…

cs.SE2026

From Candidate Admission to Task-Level Return: Auditing LLM-Generated Code under Execution Contracts

Hiroyasu Usami, Keisuke Hara, Ayato Tsuboi +1

Admission rules retain generated programs, whereas selection policies return one candidate per task. We audit how these decisions interact with execution contracts in two separatel…

cs.CL2026

LLM Judges Have Dark Current: Stratified Null and Utility Tests for LLM Judge Reliability

Hiroyasu Usami, Keisuke Hara, Ayato Tsuboi +1

Passing an exact-clone null gate does not entail passing a matched target-selection utility gate. We call a non-tie preference between exact duplicates dark current. On 102 prespec…