Author

Amir Mesbah

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.

#machine learning Preprint Oct 2026

Before We Adapt: The Zero-Shot Generalization Bottleneck in Continual World Models

It is found that zero-shot reuse can degrade substantially under physical-context changes and that this behavior depends strongly on the observation representation used by the WM, identifying representation generalization as an important bottleneck for reliable world-model reuse in CRL.

Amir Mesbah, Di Wu · 0 citations