Skip to content

Author

Chang-Ming Xu

3 papers 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.

#artificial intelligence Preprint Sep 2026

Certified Task-Conditioned Active Observability

It is proved that task-predictive equivalence induces the unique minimal sufficient quotient $\mathcal{H}/\!\sim_\tau$, leaving active observability complexity strictly invariant while eliminating superfluous distinctions.

Lin-Zhe Zhang, Chang-Ming Xu · 0 citations
#artificial intelligence Preprint Sep 2026

Discovering Physical Representation Languages

Before a machine can discover a physical law, it must discover what its measurements are: which observations live on cells, which are intensive or extensive, which sectors are dual, and which distinctions are merely gauge. We introduce physical representation-language discovery, the problem of recovering this hidden on...

Lin-Zhe Zhang, Chang-Ming Xu · 0 citations
#machine learning Preprint Sep 2026

What Can a Recurrent State Safely Forget?

Recurrent models must preserve information that changes future behavior while suppressing hidden-state error. These objectives conflict: contraction improves stability, but contraction along a future-distinguishing direction destroys memory. We formalize this boundary through the predictive quotient of a recurrent stat...

Lin-Zhe Zhang, Chang-Ming Xu · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.