English
Related papers

Related papers: DocKD: Knowledge Distillation from LLMs for Open-W…

200 papers

Large language models (LLMs) are known to memorize parts of their training data, raising important concerns around privacy and security. While previous research has focused on studying memorization in pre-trained models, much less is known…

Machine Learning · Computer Science 2025-08-19 Simardeep Singh

Multi-modal document pre-trained models have proven to be very effective in a variety of visually-rich document understanding (VrDU) tasks. Though existing document pre-trained models have achieved excellent performance on standard…

Computer Vision and Pattern Recognition · Computer Science 2025-06-19 Chuwei Luo , Guozhi Tang , Qi Zheng , Cong Yao , Lianwen Jin , Chenliang Li , Yang Xue , Luo Si

Multimodal pre-training with text, layout, and image has made significant progress for Visually Rich Document Understanding (VRDU), especially the fixed-layout documents such as scanned document images. While, there are still a large number…

Computation and Language · Computer Science 2022-03-14 Junlong Li , Yiheng Xu , Lei Cui , Furu Wei

Knowledge Distillation (KD) is a powerful approach for compressing a large model into a smaller, more efficient model, particularly beneficial for latency-sensitive applications like recommender systems. However, current KD research…

Information Retrieval · Computer Science 2024-08-28 Nikhil Khani , Shuo Yang , Aniruddh Nath , Yang Liu , Pendo Abbo , Li Wei , Shawn Andrews , Maciej Kula , Jarrod Kahn , Zhe Zhao , Lichan Hong , Ed Chi

Knowledge distillation is a key technique for transferring the capabilities of large language models (LLMs) into smaller, more efficient student models. Existing distillation approaches often overlook two critical factors: the learning…

Machine Learning · Computer Science 2026-05-13 Jincheng Cao , Fanzhi Zeng , Leqi Liu , Aryan Mokhtari

Knowledge distillation addresses the problem of transferring knowledge from a teacher model to a student model. In this process, we typically have multiple types of knowledge extracted from the teacher model. The problem is to make full use…

Computation and Language · Computer Science 2023-02-02 Chenglong Wang , Yi Lu , Yongyu Mu , Yimin Hu , Tong Xiao , Jingbo Zhu

Complex deep learning models now achieve state of the art performance for many document retrieval tasks. The best models process the query or claim jointly with the document. However for fast scalable search it is desirable to have document…

Information Retrieval · Computer Science 2019-11-26 Siamak Shakeri , Abhinav Sethy , Cheng Cheng

Recent advances in Visually-rich Document Understanding rely on large Vision-Language Models like Donut, which perform document-level Visual Question Answering without Optical Character Recognition. Despite their effectiveness, these models…

Computer Vision and Pattern Recognition · Computer Science 2025-10-01 Adnan Ben Mansour , Ayoub Karine , David Naccache

Knowledge distillation is an effective method for training small and efficient deep learning models. However, the efficacy of a single method can degenerate when transferring to other tasks, modalities, or even other architectures. To…

Computer Vision and Pattern Recognition · Computer Science 2024-03-12 Roy Miles , Ismail Elezi , Jiankang Deng

Knowledge distillation (KD) is an effective technique to transfer knowledge from one neural network (teacher) to another (student), thus improving the performance of the student. To make the student better mimic the behavior of the teacher,…

Machine Learning · Computer Science 2020-10-20 Xiang Deng , Zhongfei , Zhang

Vision-Language Models (VLMs) such as CLIP are trained on large amounts of image-text pairs, resulting in remarkable generalization across several data distributions. However, in several cases, their expensive training and data…

Computer Vision and Pattern Recognition · Computer Science 2024-03-12 Sravanti Addepalli , Ashish Ramayee Asokan , Lakshay Sharma , R. Venkatesh Babu

Knowledge Distillation (KD) has been extensively used for natural language understanding (NLU) tasks to improve a small model's (a student) generalization by transferring the knowledge from a larger model (a teacher). Although KD methods…

Machine Learning · Computer Science 2022-12-13 Aref Jafari , Ivan Kobyzev , Mehdi Rezagholizadeh , Pascal Poupart , Ali Ghodsi

Deep neural models in recent years have been successful in almost every field, including extremely complex problem statements. However, these models are huge in size, with millions (and even billions) of parameters, thus demanding more…

Computer Vision and Pattern Recognition · Computer Science 2021-06-18 Lin Wang , Kuk-Jin Yoon

Knowledge distillation (KD) is an essential technique to compress large language models (LLMs) into smaller ones. However, despite the distinct roles of the student model and the teacher model in KD, most existing frameworks still use a…

Computation and Language · Computer Science 2026-03-25 Songming Zhang , Xue Zhang , Tong Zhang , Bojie Hu , Yufeng Chen , Jinan Xu

Knowledge distillation is an effective and stable method for model compression via knowledge transfer. Conventional knowledge distillation (KD) is to transfer knowledge from a large and well pre-trained teacher network to a small student…

Computer Vision and Pattern Recognition · Computer Science 2021-11-24 Zhiqiang Liu , Yanxia Liu , Chengkai Huang

While large vision-language models (VLMs) demonstrate strong long-context understanding, their prevalent small branches fail on linguistics-photography alignment for a limited window size. We discover that knowledge distillation improves…

Computer Vision and Pattern Recognition · Computer Science 2026-01-06 Haoyi Zhou , Shuo Li , Tianyu Chen , Qi Song , Chonghan Gao , Jianxin Li

Relational understanding is critical for a number of visually-rich documents (VRDs) understanding tasks. Through multi-modal pre-training, recent studies provide comprehensive contextual representations and exploit them as prior knowledge…

Computation and Language · Computer Science 2022-05-06 Xin Li , Yan Zheng , Yiqing Hu , Haoyu Cao , Yunfei Wu , Deqiang Jiang , Yinsong Liu , Bo Ren

Sequence-level knowledge distillation (SLKD) is a model compression technique that leverages large, accurate teacher models to train smaller, under-parameterized student models. Why does pre-processing MT data with SLKD help us train…

Computation and Language · Computer Science 2019-12-10 Mitchell A. Gordon , Kevin Duh

The advancement of knowledge distillation has played a crucial role in enabling the transfer of knowledge from larger teacher models to smaller and more efficient student models, and is particularly beneficial for online and…

Computer Vision and Pattern Recognition · Computer Science 2024-03-26 Wanli Ma , Oktay Karakus , Paul L. Rosin

Large language models (LLMs) have demonstrated remarkable abilities in various natural language processing areas, but they demand high computation resources which limits their deployment in real-world. Distillation is one technique to solve…

Computation and Language · Computer Science 2025-07-31 Zhi Zhou , Sirui Miao , Xiangyu Duan , Hao Yang , Min Zhang