Yuxuan Jiang
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
126
Top categories
NLP×1AI×1
Frequent co-authors
Research Timeline
2026
Bridging Reasoning Trajectories in On-Policy Distillation via Near-Future Guidance
The paper introduces Trajectory-aware OPD (TOPD), a method that uses near-future trajectory information to improve On-Policy Distillation by accurately identifying and guiding true reasoning divergences, significantly boosting model performance.
Highlighted terms show continued research focus across papers