English
Related papers

Related papers: Demystifying OPD: Length Inflation and Stabilizati…

200 papers

On-policy distillation (OPD) has become a popular training paradigm in the LLM community. This paradigm selects a larger model as the teacher to provide dense, fine-grained signals for each sampled trajectory, in contrast to reinforcement…

Machine Learning · Computer Science 2026-04-09 Chenxu Yang , Chuanyu Qin , Qingyi Si , Minghui Chen , Naibin Gu , Dingyu Yao , Zheng Lin , Weiping Wang , Jiaqi Wang , Nan Duan

On-policy distillation (OPD) trains a student on its own trajectories under token-level teacher supervision, but existing methods are capped by a single-teacher capability ceiling: when the teacher errs, the student inherits the error. OPD…

Computation and Language · Computer Science 2026-05-05 Jianze Wang , Ying Liu , Jinlong Chen , Xuchun Hu , Qilong Zhang , Yu Cao , Jun Wang , Hua Yang , Yong Xie , Qianglong Chen

On-Policy Distillation (OPD) has gained wide attraction as an LLM post-training paradigm due to its effectiveness in improving capabilities without introducing model distribution drift, and consequently, regression in general tasks.…

Artificial Intelligence · Computer Science 2026-05-25 Aristotelis Lazaridis , Dylan Bates , Aman Sharma , Brian King , Vincent Lu , Jack FitzGerald

On-policy distillation (OPD) is a powerful paradigm for model alignment, yet its reliance on teacher logits restricts its application to white-box scenarios. We contend that structured semantic rubrics can serve as a scalable alternative to…

Machine Learning · Computer Science 2026-05-11 Junfeng Fang , Zhepei Hong , Mao Zheng , Mingyang Song , Gengsheng Li , Houcheng Jiang , Dan Zhang , Haiyun Guo , Xiang Wang , Tat-Seng Chua

On-policy distillation (OPD) trains a student on its own rollouts with token-level teacher supervision. Recent selective OPD methods exploit the non-uniformity of OPD signals by prioritizing high-entropy or high-disagreement tokens. We…

Machine Learning · Computer Science 2026-05-27 Yuanyi Wang , Su Lu , Yanggan Gu , Pengkai Wang , Yifan Yang , Zhaoyi Yan , Congkai Xie , Jianmin Wu , Hongxia Yang

Speculative decoding accelerates large language model inference by pairing a target model with a lightweight draft model whose proposed tokens are verified in parallel. A common way to build draft models, like EAGLE3 or DFlash is supervised…

Computation and Language · Computer Science 2026-05-29 Haodi Lei , Yafy Li , Haoran Zhang , Shunkai Zhang , Qianjia Cheng , Xiaoye Qu , Ganqu Cui , Bowen Zhou , Ning Ding , Yun Luo , Yu Cheng

We study {on-policy self-distillation} (OPSD), where a language model improves its reasoning ability by distilling privileged teacher distributions along its own on-policy trajectories. Despite the performance gains of OPSD, we identify a…

Machine Learning · Computer Science 2026-05-13 Yuxiao Yang , Xiaoyun Wang , Weitong Zhang

On-policy reinforcement learning has become the dominant paradigm for reasoning alignment in large language models, yet its sparse, outcome-level rewards make token-level credit assignment notoriously difficult. On-Policy Distillation (OPD)…

Machine Learning · Computer Science 2026-04-14 Binbin Zheng , Xing Ma , Yiheng Liang , Jingqing Ruan , Xiaoliang Fu , Kepeng Lin , Benchang Zhu , Ke Zeng , Xunliang Cai

Knowledge distillation improves large language model (LLM) reasoning by compressing the knowledge of a teacher LLM to train smaller LLMs. On-policy distillation advances this approach by having the student sample its own trajectories while…

Machine Learning · Computer Science 2026-03-23 Siyan Zhao , Zhihui Xie , Mengchen Liu , Jing Huang , Guan Pang , Feiyu Chen , Aditya Grover

Reinforcement learning for large language models faces a fundamental trade-off between sample efficiency and asymptotic performance: strictly on-policy methods discard trajectories after a single update, while off-policy reuse introduces…

Machine Learning · Computer Science 2026-05-26 Changyu Chen , Xiting Wang , Rui Yan

Reinforcement learning has emerged as a powerful tool for improving diffusion-based text-to-image models, but existing methods are largely limited to single-task optimization. Extending RL to multiple tasks is challenging: joint…

Machine Learning · Computer Science 2026-05-15 Quanhao Li , Junqiu Yu , Kaixun Jiang , Yujie Wei , Zhen Xing , Pandeng Li , Ruihang Chu , Shiwei Zhang , Yu Liu , Zuxuan Wu

On-policy distillation (OPD) has become a promising paradigm for reasoning-oriented post-training of large language models (LLMs), especially when combined with reinforcement learning from verifiable rewards (RLVR). Existing OPD methods…

On-policy self-distillation (OPSD) improves the reasoning performance of large language models (LLMs) by providing dense token-level supervision for on-policy rollouts. However, existing OPSD methods often yield limited gains on in-domain…

Computation and Language · Computer Science 2026-05-28 Ziqi Zhao , Xinyu Ma , Liu Yang , Yujie Feng , Daiting Shi , Jingzhou He , Xin Xin , Zhaochun Ren , Xiao-Ming Wu

Context distillation enables language models to internalize in-context knowledge into their parameters. In our work, we propose On-Policy Context Distillation (OPCD), a framework that bridges on-policy distillation with context distillation…

Computation and Language · Computer Science 2026-03-24 Tianzhu Ye , Li Dong , Xun Wu , Shaohan Huang , Furu Wei

Moving beyond simple scalar rewards toward richer world feedback is a natural path to more scalable RL post-training. On-policy self-distillation (OPSD) is a promising recent approach that uses arbitrary feedback as learning signal, yet its…

Machine Learning · Computer Science 2026-05-29 Tommy He , Jerome Sieber , Matteo Saponati

On-policy self-distillation (OPSD) is an emerging LLM post-training paradigm in which the model serves as its own teacher: conditioned on privileged information such as a reference trace or hint, the same policy provides dense token-level…

Machine Learning · Computer Science 2026-05-22 Hongbin Zhang , Chaozheng Wang , Kehai Chen , Youcheng Pan , Yang Xiang , Jinpeng Wang , Min Zhang

Standard knowledge distillation for autoregressive models often suffers from distribution mismatch. While on-policy methods mitigate this by leveraging student-generated outputs, they rely on computationally expensive Reinforcement Learning…

Machine Learning · Computer Science 2026-05-08 Miao Rang , Zhenni Bi , Hang Zhou , Kai Han , Xuechun Wang , An Xiao , Xinghao Chen , Yunhe Wang , Hanting Chen

On-policy distillation is pivotal for transferring reasoning capabilities to capacity-constrained models, yet remains prone to instability and negative transfer. We show that on-policy distillation can be interpreted, both theoretically and…

Machine Learning · Computer Science 2026-03-13 Jongwoo Ko , Sara Abdali , Young Jin Kim , Tianyi Chen , Pashmina Cameron

Existing Flow Matching (FM) text-to-image models suffer from two critical bottlenecks under multi-task alignment: the reward sparsity induced by scalar-valued rewards, and the gradient interference arising from jointly optimizing…

Computer Vision and Pattern Recognition · Computer Science 2026-05-26 Zhen Fang , Wenxuan Huang , Yu Zeng , Yiming Zhao , Shuang Chen , Kaituo Feng , Yunlong Lin , Lin Chen , Zehui Chen , Shaosheng Cao , Feng Zhao

Knowledge distillation optimises a smaller student model to behave similarly to a larger teacher model, retaining some of the performance benefits. While this method can improve results on in-distribution examples, it does not necessarily…

Computation and Language · Computer Science 2024-07-26 Joe Stacey , Marek Rei