Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Akarsh Kumar

Akarsh Kumar

1 indexed paper

Recent (6 mo)
1
With code
0
Influential cites
0
Benchmarked
0

Publications per year

1
26

Top categories

ML×1AI×1

Frequent co-authors

Phillip Isola1×

Research Timeline

2026
Pretraining Recurrent Networks without Recurrence

This paper proposes Supervised Memory Training (SMT), a method for training nonlinear RNNs that sidesteps recurrent credit propagation entirely.

Highlighted terms show continued research focus across papers

Papers

cs.LGcs.AIEmpiricalComprehensiveRecentJun 4, 2026

Pretraining Recurrent Networks without Recurrence

Akarsh Kumar, Phillip Isola

This paper proposes Supervised Memory Training (SMT), a method for training nonlinear RNNs that sidesteps recurrent credit propagation entirely.

View →