中文
相关论文

相关论文: Counteraction-Aware Multi-Teacher On-Policy Distil…

200 篇论文

On-policy distillation (OPD) is increasingly used in LLM post-training because it can leverage a teacher model to provide dense supervision on student rollouts. The standard implementation, however, usually reduces distribution matching to…

机器学习 · 计算机科学 2026-04-28 Yuqian Fu , Haohuan Huang , Kaiwen Jiang , Jiacai Liu , Zhuo Jiang , Yuanheng Zhu , Dongbin Zhao

On-policy distillation (OPD) has shown strong potential for transferring reasoning ability from frontier or domain-specific models to smaller students. While effective on static single-turn tasks, its behavior in multi-turn agent settings…

机器学习 · 计算机科学 2026-04-30 Jiaqi Wang , Wenhao Zhang , Weijie Shi , Yaliang Li , James Cheng

On-policy distillation (OPD) is an increasingly important paradigm for post-training language models. However, we identify a pervasive Scaling Law of Miscalibration: while OPD effectively improves task accuracy, it systematically traps…

机器学习 · 计算机科学 2026-04-21 Jiaxin Zhang , Xiangyu Peng , Qinglin Chen , Qinyuan Ye , Caiming Xiong , Chien-Sheng Wu

Large language models are often post-trained with sparse verifier rewards, which indicate whether a sampled trajectory succeeds but provide limited guidance about where reasoning succeeds or fails. On-policy distillation (OPD) offers denser…

As Large Language Models (LLMs) continue to grow in both capability and cost, transferring frontier capabilities into smaller, deployable students has become a central engineering problem, and knowledge distillation remains the dominant…

机器学习 · 计算机科学 2026-05-19 Mingyang Song , Mao Zheng

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…

计算与语言 · 计算机科学 2026-05-05 Jianze Wang , Ying Liu , Jinlong Chen , Xuchun Hu , Qilong Zhang , Yu Cao , Jun Wang , Hua Yang , Yong Xie , Qianglong Chen

Large language models (LLMs) often solve a task when all instructions are given in a single prompt, but fail when the same information is revealed gradually across turns. When a clean FULL prompt and a RAW-SHARDED conversation contain the…

计算与语言 · 计算机科学 2026-05-29 Zizhuo Lin , Quanling Liu , Jinsheng Quan , Chao Zhang , Yifan Zhu , Xing Shi , Jingtao Xu , Zhihui Li , Yawei Luo

On-policy distillation (OPD) trains a student model on its own rollouts using dense feedback from a stronger teacher. Prior literature suggests that, provided teacher feedback is available, supervising the full sequence of response tokens…

计算与语言 · 计算机科学 2026-05-26 Kaiyuan Liu , Ziyuan Zhuang , Yang Bai , Bing Wang , Rongxiang Weng , Jieping Ye

Recently, multi-modal content generation has attracted lots of attention from researchers by investigating the utilization of visual instruction tuning based on large language models (LLMs). To enhance the performance and generalization…

计算机视觉与模式识别 · 计算机科学 2023-11-15 Xinwei Li , Li Lin , Shuai Wang , Chen Qian

Learning from demonstrations in embodied control is often cast as behavioral cloning, and recent diffusion or flow-matching policies improve this paradigm by modeling multi-modal expert actions. Yet these methods remain offline supervised…

机器学习 · 计算机科学 2026-05-27 Zhenglin Wan , Jingxuan Wu , Xingrui Yu , Chubin Zhang , Mingcong Lei , Bo An , Ivor W. Tsang , Yang You

On-policy distillation (OPD) has recently emerged as an effective post-training paradigm for consolidating the capabilities of specialized expert models into a single student model. Despite its empirical success, the conditions under which…

On-policy distillation (OPD) trains a student on its own trajectories with token-level teacher feedback and often outperforms off-policy distillation and standard reinforcement learning. However, we find that its standard advantage weighted…

机器学习 · 计算机科学 2026-05-14 Nan Jia , Haojin Yang , Xing Ma , Jiesong Lian , Shuailiang Zhang , Weipeng Zhang , Ke Zeng , Xunliang Cai , Zequn Sun

On-policy distillation (OPD), which aligns the student with the teacher's logit distribution on student-generated trajectories, has demonstrated strong empirical gains in improving student performance and often outperforms off-policy…

机器学习 · 计算机科学 2026-02-27 Wenkai Yang , Weijie Liu , Ruobing Xie , Kai Yang , Saiyong Yang , Yankai Lin

Black-box knowledge distillation for large language models presents a strict trade-off. Simple off-policy methods (e.g., sequence-level knowledge distillation) struggle to correct the student's inherent errors. Fully on-policy methods…

On-policy distillation (OPD) and on-policy self-distillation (OPSD) have emerged as promising post-training methods for large language models, offering dense token-level supervision on trajectories sampled from the model's own policy.…

人工智能 · 计算机科学 2026-05-26 Siqi Zhu , Xuyan Ye , Hongyu Lu , Weiye Shi , Ge Liu

RLVR and OPD have become standard paradigms for post-training. We provide a unified analysis of these two paradigms in consolidating multiple expert capabilities into a single model, identifying capability loss in different ways: mixed RLVR…

机器学习 · 计算机科学 2026-05-01 Naibin Gu , Chenxu Yang , Qingyi Si , Chuanyu Qin , Dingyu Yao , Peng Fu , Zheng Lin , Weiping Wang , Nan Duan , Jiaqi Wang

On-Policy Distillation (OPD) has emerged as a dominant post-training paradigm for large language models, especially for reasoning domains. However, OPD remains unstable in practice due to the high gradient variance of its single-sample…

机器学习 · 计算机科学 2026-05-11 Minjae Oh , Sangjun Song , Gyubin Choi , Yunho Choi , Yohan Jo

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…

机器学习 · 计算机科学 2026-05-27 Yuanyi Wang , Su Lu , Yanggan Gu , Pengkai Wang , Yifan Yang , Zhaoyi Yan , Congkai Xie , Jianmin Wu , Hongxia Yang

On-policy distillation (OPD) has become a core technique in the post-training of large language models, yet its training dynamics remain poorly understood. This paper provides a systematic investigation of OPD dynamics and mechanisms. We…

Knowledge distillation (KD) is an effective model compression technique where a compact student network is taught to mimic the behavior of a complex and highly trained teacher network. In contrast, Mutual Learning (ML) provides an…

计算机视觉与模式识别 · 计算机科学 2021-10-25 Usma Niyaz , Deepti R. Bathula
‹ 上一页 1 2 3 10 下一页 ›