English
Related papers

Related papers: Preference-Based Self-Distillation: Beyond KL Matc…

200 papers

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…

Computation and Language · Computer Science 2026-01-30 Jing Xiong , Hui Shen , Shansan Gong , Yuxin Cheng , Jianghan Shen , Chaofan Tao , Haochen Tan , Haoli Bai , Lifeng Shang , Ngai Wong

We introduce Proximal Policy Distillation (PPD), a novel policy distillation method that integrates student-driven distillation and Proximal Policy Optimization (PPO) to increase sample efficiency and to leverage the additional rewards that…

Machine Learning · Computer Science 2026-05-11 Giacomo Spigler

Reinforcement learning from verifiable rewards (RLVR) suffers from sparse outcome signals, creating severe exploration bottlenecks on complex reasoning tasks. Recent on-policy self-distillation methods attempt to address this by utilizing…

Machine Learning · Computer Science 2026-05-20 Yang Li , Erik Nijkamp , Semih Yavuz , Shafiq Joty

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…

Machine Learning · Computer Science 2026-05-14 Nan Jia , Haojin Yang , Xing Ma , Jiesong Lian , Shuailiang Zhang , Weipeng Zhang , Ke Zeng , Xunliang Cai , Zequn Sun

Self-Distillation Policy Optimization (SDPO) provides dense token-level credit assignment for reinforcement learning with large language models by leveraging the model's own feedback-conditioned predictions as a self-teacher. Unlike GRPO,…

Machine Learning · Computer Science 2026-05-28 Zehao Liu , Yuanpu Cao , Jinghui Chen , Vasant G. Honavar

Due to constraints on privacy, cost, and latency, on-premise deployment of small models is increasingly common. However, most practical pipelines stop at supervised fine-tuning (SFT) and fail to reach the reinforcement learning (RL)…

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

The push to compress and impart the proficiency of Large Language Models (LLMs) into more deployable and efficient Small Language Models (SLMs) has benefited from improvements in knowledge distillation (KD) techniques. These techniques…

Artificial Intelligence · Computer Science 2025-07-02 Shreyansh Padarha

In learning-to-rank problems, a privileged feature is one that is available during model training, but not available at test time. Such features naturally arise in merchandised recommendation systems; for instance, "user clicked this item"…

Machine Learning · Computer Science 2022-09-20 Shuo Yang , Sujay Sanghavi , Holakou Rahmanian , Jan Bakus , S. V. N. Vishwanathan

We introduce a novel approach to large language model (LLM) distillation by formulating it as a constrained reinforcement learning problem. While recent work has begun exploring the integration of task-specific rewards into distillation…

Machine Learning · Computer Science 2025-09-30 Matthieu Zimmer , Xiaotong Ji , Tu Nguyen , Haitham Bou Ammar

Advances in self-distillation have shown that when knowledge is distilled from a teacher to a student using the same deep learning (DL) architecture, the student performance can surpass the teacher particularly when the network is…

Machine Learning · Computer Science 2025-06-25 Muhammad Haseeb Aslam , Clara Martinez , Marco Pedersoli , Alessandro Koerich , Ali Etemad , Eric Granger

The transfer of knowledge from one policy to another is an important tool in Deep Reinforcement Learning. This process, referred to as distillation, has been used to great success, for example, by enhancing the optimisation of agents,…

On-policy distillation (OPD) leverages dense teacher rewards to enhance reasoning models. However, scaling OPD to long-horizon tasks exposes a critical flaw: as the student's generated prefix inevitably diverges from the teacher's thought…

Machine Learning · Computer Science 2026-05-29 Zhicheng Yang , Zhijiang Guo , Yifan Song , Minrui Xu , Yongxin Wang , Yiwei Wang , Xiaodan Liang , Jing Tang

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

In the field of large language models (LLMs), Knowledge Distillation (KD) is a critical technique for transferring capabilities from teacher models to student models. However, existing KD methods face limitations and challenges in…

Computation and Language · Computer Science 2025-04-08 Yixing Li , Yuxian Gu , Li Dong , Dequan Wang , Yu Cheng , Furu Wei

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 is a promising approach for transferring knowledge between language models, where a student learns from dense token-level signals along its own trajectories. This framework typically uses reverse KL divergence,…

Machine Learning · Computer Science 2026-05-25 Woogyeol Jin , Taywon Min , Yongjin Yang , Swanand Ravindra Kadhe , Yi Zhou , Dennis Wei , Nathalie Baracaldo , Kimin Lee

Large language models are increasingly post-trained with reinforcement learning in verifiable domains such as code and math. Yet, current methods for reinforcement learning with verifiable rewards (RLVR) learn only from a scalar outcome…

Self-distillation bootstraps large language models (LLMs) by training on their own generations. However, existing methods either rely on external signals to curate self-generated outputs (e.g., correctness filtering, execution feedback, and…

Computation and Language · Computer Science 2026-05-22 Guangya Hao , Yitong Shang , Yunbo Long , Zhuokai Zhao , Hanxue Liang

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…

Machine Learning · Computer Science 2026-05-27 Zhenglin Wan , Jingxuan Wu , Xingrui Yu , Chubin Zhang , Mingcong Lei , Bo An , Ivor W. Tsang , Yang You