Author

Zihan Liu

Chinese University of Hong KongORCID 0000-0001-7147-7218Unclaimed ORCID profile · follow to get notified of new preprints

Additional preprints under this name without ORCID

Zihan Liu1 paper · King's College London

Biology Disciplines

Click to filter author papers

Neuroscience· 1

Signature Assays, Organisms & Methods

Click to filter · or open tag

Approach:statistical model· 1

Frequent Co-Authors

Anno Christopher KurthiD· 1 shared Toshitake AsabukiiD· 1 shared Yuma OsakoiD· 1 shared

Activity by Year

2026-2026 · peak 1/yr

Co-Author Collaboration Network

3 top collaborators · 3 mutual co-author links

Click any collaborator node to inspect or filter shared papers

Focal author (center)Selected co-authorORCID co-authorUnlinked name

Curved chords = mutual co-authorship

1 shared paperNeuroscience

Anno Christopher KurthORCID

Mutual co-authors in cluster

Author profile →

1 paper

Recent·Most cited

NeurosciencebioRxivPreprintFeb 16, 2026

Learning sculpts orthogonal task manifolds for continual skill learning in recurrent networks

Zihan Liu, Anno Christopher Kurth, Yuma Osako, Toshitake Asabuki

This paper shows that recurrent neural networks can learn new tasks without forgetting old ones by preserving task-specific latent dynamics through orthogonal task manifolds.

DOI 10.64898/2026.02.15.705283

statistical model