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

Nikita Balagansky

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

Daniil Plyusov1×
Alexey Gorbatovski1×
Alexey Malakhov1×
Boris Shaposhnikov1×
Daria Korotyshova1×
Daniil Gavrilov1×

Research Timeline

2026
Trust-Region Behavior Blending for On-Policy Distillation

The paper introduces Trust-Region behavior Blending (TRB), a warmup method that improves on-policy distillation by replacing poor early student rollouts with teacher-aligned behavior policies, leading to state-of-the-art performance on math-reasoning tasks.

Highlighted terms show continued research focus across papers

Papers

cs.LGcs.AIRecentMay 29, 2026

Trust-Region Behavior Blending for On-Policy Distillation

Daniil Plyusov, Alexey Gorbatovski, Alexey Malakhov, Nikita Balagansky +3 more

The paper introduces Trust-Region behavior Blending (TRB), a warmup method that improves on-policy distillation by replacing poor early student rollouts with teacher-aligned behavior policies, leading…

View →