Author

Masha Itkina

2 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

The Gaussian Is Enough: Flow-Matching Priors Do Not Help When Fine-Tuning Large Behavior Models

It is found that fine-tuned imitation learning policies converge to similar action predictions across priors, despite their fine-tuned encoder embeddings diverging substantially from the pretrained embeddings and each other.

Chen Xu, Rishi Shah, H. Kress-Gazit et al. · 0 citations

Preprint Aug 2026

Memory Anchors for Continual Robot Learning

This work identifies Memory Anchors in regions where representations of new-task observations collapse onto those of old-task observations even though the tasks require conflicting actions, like when a familiar object must be manipulated in a new way.

Maximilian Du, Zhanyi Sun, Chen Xu et al. · 1 citation