Episode
DOPD: Dual On-policy Distillation
- Podcast
- Daily Paper Cast
- Published
- Jul 2, 2026
- Duration seconds
- 1526
- Processing state
not_requested- Canonical source
- https://share.transistor.fm/s/ba4a0597
Actions
POST https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/dopd-dual-on-policy-distillation/transcription-requests
Idempotently request low-priority transcript generation for this episode.GET https://stenobird.com/podcast/daily-paper-cast-7079649/dopd-dual-on-policy-distillation.md
Read the agent-friendly Markdown representation of this episode resource.
Summary
🤗 Upvotes: 80 | cs.AI Authors: Xinlei Yu, Gen Li, Qingyi Si, Guibin Zhang, Yuqi Xu, Congcong Wang, Shuai Dong, Kaiwen Tuo, Xiangyu Zeng, Kaituo Feng, Qunzhong Wang, Yang Shi, Xiaobin Hu, Xiangyu Yue, Jiaqi Wang, Shuicheng Yan Title: DOPD: Dual On-policy Distillation Arxiv: http://arxiv.org/abs/2606.30626v1 Abstract: On-policy distillation (OPD) offers superior capacity transfer by supervising student-sampled trajectories with dense token-level signals. To furnish high-quality supervision sources and thereby elevate the performance frontier of distillation, an intuitive direction is to infuse privileged information to either teacher or student itself. However, this additional input induces a potential failure mode we dub privilege illusion: a pattern that conflates the transferable capability gap that students are meant to close, and the information asymmetry gap that can only be mimicked but never replicated. This issue is further amplified by the inherent non-uniformity of token-level supervision, where only a small subset of tokens carries pivotal capability-bearing signals. To this end, we propose DOPD, an advantage-aware dual distillation paradigm that dynamically routes token-level supervision between privileged teacher and privileged student policies based on their advantage gap and relative probabilities. Each token receives supervision of different strength, objective, and strategy from either teacher or student itself, which transfers credible capability while simultaneously receiving auxiliary signals, to alleviate privilege illusion. Extensive experiments on both large language model (LLM) and vision-language model (VLM) settings demonstrate that DOPD consistently outperforms Vanilla OPD and other counterparts. Further results on stability, robustness, conti…