English
Related papers

Related papers: Distribution Corrected Offline Data Distillation f…

200 papers

Reasoning distillation has attracted increasing attention. It typically leverages a large teacher model to generate reasoning paths, which are then used to fine-tune a student model so that it mimics the teacher's behavior in training…

Computation and Language · Computer Science 2026-02-24 Kaiyuan Liu , Shaotian Yan , Rui Miao , Bing Wang , Chen Shen , Jun Zhang , Jieping Ye

We propose the task of knowledge distillation detection, which aims to determine whether a student model has been distilled from a given teacher, under a practical setting where only the student's weights and the teacher's API are…

Machine Learning · Computer Science 2025-10-03 Qin Shi , Amber Yijia Zheng , Qifan Song , Raymond A. Yeh

Distilling reasoning paths from teacher to student models via supervised fine-tuning (SFT) provides a shortcut for improving the reasoning ability of smaller Large Language Models (LLMs). However, the reasoning paths generated by teacher…

Computation and Language · Computer Science 2026-02-03 Shicheng Xu , Liang Pang , Yunchang Zhu , Jia Gu , Zihao Wei , Jingcheng Deng , Feiyang Pan , Huawei Shen , Xueqi Cheng

With the rapid development of deep learning, large language models have shown strong capabilities in complex reasoning tasks such as mathematical equation solving. However, their substantial computational and storage costs hinder practical…

Machine Learning · Computer Science 2025-11-25 Fengming Yu , Qingyu Meng , Haiwei Pan , Kejia Zhang

Large Reasoning Models(LRMs) such as OpenAI o1 and DeepSeek-R1 have shown remarkable reasoning capabilities by scaling test-time compute and generating long Chain-of-Thought(CoT). Distillation--post-training on LRMs-generated data--is a…

Machine Learning · Computer Science 2025-06-03 Huifeng Yin , Yu Zhao , Minghao Wu , Xuanfan Ni , Bo Zeng , Hao Wang , Tianqi Shi , Liangying Shao , Chenyang Lyu , Longyue Wang , Weihua Luo , Kaifu Zhang

Knowledge distillation is a critical technique to transfer knowledge between models, typically from a large model (the teacher) to a more fine-grained one (the student). The objective function of knowledge distillation is typically the…

Computation and Language · Computer Science 2021-06-03 Xinyu Wang , Yong Jiang , Zhaohui Yan , Zixia Jia , Nguyen Bach , Tao Wang , Zhongqiang Huang , Fei Huang , Kewei Tu

Enhancing small language models for real-life application deployment is a significant challenge facing the research community. Due to the difficulties and costs of using large language models, researchers are seeking ways to effectively…

Computation and Language · Computer Science 2024-09-20 Mohamad Ballout , Ulf Krumnack , Gunther Heidemann , Kai-Uwe Kühnberger

Reasoning distillation has emerged as an effective approach to enhance the reasoning capabilities of smaller language models. However, the impact of large-scale reasoning distillation on other critical abilities, particularly in-context…

Computation and Language · Computer Science 2025-07-22 Yifei Wang

We propose a distillation scaling law that estimates distilled model performance based on a compute budget and its allocation between the student and teacher. Our findings mitigate the risks associated with large-scale distillation by…

Machine Learning · Computer Science 2025-07-28 Dan Busbridge , Amitis Shidani , Floris Weers , Jason Ramapuram , Etai Littwin , Russ Webb

Knowledge distillation is a common technique for improving the performance of a shallow student network by transferring information from a teacher network, which in general, is comparatively large and deep. These teacher networks are…

Computer Vision and Pattern Recognition · Computer Science 2023-02-23 Ishan Mishra , Sethu Vamsi Krishna , Deepak Mishra

On-policy self-distillation has become a strong recipe for LLM reasoning, where a privileged teacher supervises the student's own rollouts while conditioning on the reference solution. A design choice shared by nearly all such methods,…

Artificial Intelligence · Computer Science 2026-05-28 Zihao Han , Tiangang Zhang , Huaibin Wang , Yilun Sun

Often we wish to transfer representational knowledge from one neural network to another. Examples include distilling a large network into a smaller one, transferring knowledge from one sensory modality to a second, or ensembling a…

Machine Learning · Computer Science 2022-01-26 Yonglong Tian , Dilip Krishnan , Phillip Isola

In this report, we introduce DASD-4B-Thinking, a lightweight yet highly capable, fully open-source reasoning model. It achieves SOTA performance among open-source models of comparable scale across challenging benchmarks in mathematics,…

Machine Learning · Computer Science 2026-01-15 Shaotian Yan , Kaiyuan Liu , Chen Shen , Bing Wang , Sinan Fan , Jun Zhang , Yue Wu , Zheng Wang , Jieping Ye

Knowledge distillation aims to enhance the performance of a lightweight student model by exploiting the knowledge from a pre-trained cumbersome teacher model. However, in the traditional knowledge distillation, teacher predictions are only…

Machine Learning · Computer Science 2023-05-26 Shiya Luo , Defang Chen , Can Wang

Existing knowledge distillation methods mostly focus on distillation of teacher's prediction and intermediate activation. However, the structured representation, which arguably is one of the most critical ingredients of deep models, is…

Computer Vision and Pattern Recognition · Computer Science 2024-07-16 Jing Yang , Xiatian Zhu , Adrian Bulat , Brais Martinez , Georgios Tzimiropoulos

Reasoning LLMs are trained to verbalize their reasoning process, yielding strong gains on complex tasks. This transparency also opens a promising direction: multiple reasoners can directly collaborate on each other's thinking within a…

Artificial Intelligence · Computer Science 2026-03-04 Aochong Oliver Li , Tanya Goyal

Knowledge distillation transfers knowledge from a large model to a small one via task and distillation losses. In this paper, we observe a trade-off between task and distillation losses, i.e., introducing distillation loss limits the…

Computer Vision and Pattern Recognition · Computer Science 2023-07-18 Borui Zhao , Quan Cui , Renjie Song , Jiajun Liang

Structured prediction models aim at solving a type of problem where the output is a complex structure, rather than a single variable. Performing knowledge distillation for such models is not trivial due to their exponentially large output…

Machine Learning · Computer Science 2022-03-10 Wenye Lin , Yangming Li , Lemao Liu , Shuming Shi , Hai-tao Zheng

Large recommendation models have demonstrated substantial potential gains under scaling laws, yet these gains are difficult to realize in industrial recommendation systems because real-world deployment requires lightweight models with…

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