中文
相关论文

相关论文: Teacher-Guided Policy Optimization for On-Policy R…

200 篇论文

Adapting large language models (LLMs) to long-context tasks requires post-training methods that remain accurate and coherent over thousands of tokens. Existing approaches are limited in several ways: 1) off-policy methods such as supervised…

计算与语言 · 计算机科学 2026-05-13 Miguel Moura Ramos , Duarte M. Alves , André F. T. Martins

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…

机器学习 · 计算机科学 2026-03-23 Siyan Zhao , Zhihui Xie , Mengchen Liu , Jing Huang , Guan Pang , Feiyu Chen , Aditya Grover

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

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…

机器学习 · 计算机科学 2026-04-09 Chenxu Yang , Chuanyu Qin , Qingyi Si , Minghui Chen , Naibin Gu , Dingyu Yao , Zheng Lin , Weiping Wang , Jiaqi Wang , Nan Duan

Reinforcement learning (RL) has emerged as a promising paradigm for inducing explicit reasoning behaviors in large language and vision-language models. However, reasoning-oriented RL post-training remains fundamentally challenging due to…

人工智能 · 计算机科学 2026-05-13 Fan Yang , Rui Meng , Trudi Di Qi , Ali Ezzati , Yuxin Wen

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…

机器学习 · 计算机科学 2026-05-13 Yuxiao Yang , Xiaoyun Wang , Weitong Zhang

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

Reinforcement learning has emerged as a principled post-training paradigm for Temporal Video Grounding (TVG) due to its on-policy optimization, yet existing GRPO-based methods remain fundamentally constrained by sparse reward signals and…

计算机视觉与模式识别 · 计算机科学 2026-05-15 Jiaze Li , Hao Yin , Haoran Xu , Boshen Xu , Wenhui Tan , Zewen He , Jianzhong Ju , Zhenbo Luo , Jian Luan

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…

机器学习 · 计算机科学 2026-03-13 Jongwoo Ko , Sara Abdali , Young Jin Kim , Tianyi Chen , Pashmina Cameron

Direct Preference Optimization (DPO) is a powerful paradigm to align language models with human preferences using pairwise comparisons. However, its binary win-or-loss supervision often proves insufficient for training small models with…

计算与语言 · 计算机科学 2025-09-23 Minchan Kwon , Junwon Ko , Kangil Kim , Junmo Kim

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…

机器学习 · 计算机科学 2026-05-22 Hongbin Zhang , Chaozheng Wang , Kehai Chen , Youcheng Pan , Yang Xiang , Jinpeng Wang , Min Zhang

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

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…

On-policy distillation is an efficient alternative to reinforcement learning, offering dense token-level training signals. However, its reliance on a stronger external teacher has driven recent work on on-policy self-distillation, where the…

机器学习 · 计算机科学 2026-05-07 Xin Yu , Liuchen Liao , Yiwen Zhang , Yingchen Yu , Lingzhou Xue , Qinzhen Guo

Knowledge distillation offers a promising path to transfer reasoning capabilities from large teacher models to efficient student models; however, existing token-level on-policy distillation methods require token-level alignment between the…

计算与语言 · 计算机科学 2026-01-30 Jing Xiong , Hui Shen , Shansan Gong , Yuxin Cheng , Jianghan Shen , Chaofan Tao , Haochen Tan , Haoli Bai , Lifeng Shang , Ngai Wong

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…

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…

Large language models (LLMs) have recently demonstrated strong potential for autonomous vehicle motion planning by reformulating trajectory prediction as a language generation problem. However, deploying capable LLMs in resource-constrained…

机器人学 · 计算机科学 2026-04-10 Amirhossein Afsharrad , Amirhesam Abedsoltan , Ahmadreza Moradipari , Sanjay Lall

Training vision-language models (VLMs) for complex reasoning remains a challenging task, i.a. due to the scarcity of high-quality image-text reasoning data. Conversely, text-based reasoning resources are abundant and scalable, but it is…

计算机视觉与模式识别 · 计算机科学 2025-10-29 Walid Bousselham , Hilde Kuehne , Cordelia Schmid

On-policy distillation (OPD), which supervises a student on its own sampled trajectories, has emerged as a data-efficient post-training method for improving reasoning while avoiding the reward dependence of reinforcement learning and the…

计算机视觉与模式识别 · 计算机科学 2026-05-14 Ke Zhang , Yunjie Tian , Dongdi Zhao , Yijiang Li , Yuanye Liu , Vishal M Patel , Di Fu
‹ 上一页 1 2 3 10 下一页 ›