activity
20212026
most citedDecomposing Normal and Abnormal Features of Medical Images into Discrete Latent Codes for Content-Based Image Retrieval

2 citations · 2 across the 2 of their papers we have counts for

collaborators
Showing cs.AIShow all

1 paper · 1 filter

cs.AI2026

Rules or Character? Scaling Laws for AI Safety Design

Satoshi Takahashi, Nobuji Kouno, Masaaki Komatsu +1

Artificial Intelligence (AI) safety systems combine character shaping (e.g., Reinforcement Learning from Human Feedback [RLHF], Constitutional AI), which modifies behavioral distri…