3 papers
cs.LG2026
Matched Specialization, Different Adaptation: Second-Moment Structure in Shared Representations
Toru Takahashi
Small Adam-trained shared-representation networks can reach equivalent selected mean readout measurements yet respond differently to the same further learning. We use state interve…
cs.AI2026
Toward AI That Understands Self and Others: A World-Model Theory of Cognitive Diversity and Alignment
Toru Takahashi
Modern societies possess more information than ever before, yet they do not converge toward a single shared understanding. The same events, facts, laws, technologies, or risks can…
cs.AI2026
Why Conclusions Diverge from the Same Observations: Formalizing World-Model Non-Identifiability via an Inference
Toru Takahashi
When people share the same documents and observations yet reach different conclusions, the disagreement often shifts into a judgment that the other party is cognitively defective,…