Author

Xinzhuo Cao

View on Semantic Scholar

1 paper indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Jul 2026

The Objective Decides: When a Learned Dynamics Model Uses a Conserved Quantity

It is argued that causal deployment, not decodability, is what interpretability should measure when the question is whether a model uses a piece of knowledge, and a cheap instrument for measuring it is given.

Chih-Ting Liao, Xinzhuo Cao · 0 citations