Observation record / arXiv · 人工智能

TeachBack: Learning to Teach via Bidirectional Preference Optimization for On-Policy Self-Distillation

First seen 10/22, 12:54 · Last observed 10/23, 00:55 · Source data is current

Title-based outlineTeachBack: Learning to Teach via Bidirectional Preference Optimization for On-Policy Self-Distillation

Why it mattersResearch metadata links to papers and authors. Read the original for conclusions; publication order is not impact.

Published 10/22, 12:00

30 minutesRank movement—

Building history

1 hourRank movement—

Building history

24 hoursRank movement—

Building history

Publication position history

3 observations

Publication feed in source order. Position changes do not count as heat or momentum.

arXiv metadata CC0; papers retain individual licenses· Author Linfei Ji (Huazhong University of Science and Technology), Jiayun Li (Tsinghua University), Haozhao

View original observation times and ranks

Observation time (Beijing)	Source position
10/23, 00:55	34
10/22, 18:54	34
10/22, 12:54	34

Daily aggregate history

日期	Best daily position	Last daily position	Observations
2026-10-22	34	34	2
2026-10-23	34	34	1