Pan He
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
126
Top categories
ML×1AI×1Vision×1
Frequent co-authors
Research Timeline
2026
OISD: On-Policy Internal Self-Distillation of Language Models
The OISD framework improves language model reasoning by distilling on-policy predictive signals from the final output layer to intermediate representations, leading to substantial improvements on mathematical reasoning tasks.
Highlighted terms show continued research focus across papers
Papers
cs.LGcs.AIcs.CVRecentMay 27, 2026
OISD: On-Policy Internal Self-Distillation of Language Models
Xinyu Liu, Darryl Cherian Jacob, Yang Zhou, Jindong Wang +1 more
The OISD framework improves language model reasoning by distilling on-policy predictive signals from the final output layer to intermediate representations, leading to substantial improvements on math…
View →