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

Clive Bai

2 indexed papers

Recent (6 mo)
2
With code
0
Influential cites
0
Benchmarked
0

Publications per year

2
26

Top categories

ML×2AI×2

Frequent co-authors

Kun Liang2×
Chenming Tang2×
Weijie Liu2×
Saiyong Yang2×
Yunfang Wu2×

Research Timeline

2026
ADWIN: Adaptive Windows for Horizon-Aware On-Policy Distillation

ADWIN introduces an adaptive window framework for on-policy distillation (OPD) that efficiently manages the supervision horizon by training on short, teacher-anchored prefixes while using delayed full-rollout probes to maintain alignment, significantly reducing training cost while preserving accuracy.

ADWIN: Adaptive Windows for Horizon-Aware On-Policy Distillation

ADWIN introduces an adaptive window framework for on-policy distillation (OPD) that efficiently manages the supervision horizon by training on short, teacher-anchored prefixes while using delayed full-rollout probes to maintain alignment, significantly reducing training cost while preserving accuracy.

Highlighted terms show continued research focus across papers

Papers

cs.LGcs.AIRecentMay 27, 2026

ADWIN: Adaptive Windows for Horizon-Aware On-Policy Distillation

Kun Liang, Chenming Tang, Clive Bai, Weijie Liu +2 more

ADWIN introduces an adaptive window framework for on-policy distillation (OPD) that efficiently manages the supervision horizon by training on short, teacher-anchored prefixes while using delayed full…

View →
cs.LGcs.AIRecentMay 27, 2026

ADWIN: Adaptive Windows for Horizon-Aware On-Policy Distillation

Kun Liang, Chenming Tang, Clive Bai, Weijie Liu +2 more

ADWIN introduces an adaptive window framework for on-policy distillation (OPD) that efficiently manages the supervision horizon by training on short, teacher-anchored prefixes while using delayed full…

View →