English
Related papers

Related papers: PRISM: Diversifying Dataset Distillation by Decoup…

200 papers

Knowledge distillation has become increasingly important in model compression. It boosts the performance of a miniaturized student network with the supervision of the output distribution and feature maps from a sophisticated teacher…

Machine Learning · Computer Science 2020-08-04 Yushuo Guan , Pengyu Zhao , Bingxuan Wang , Yuanxing Zhang , Cong Yao , Kaigui Bian , Jian Tang

Knowledge distillation allows smaller neural networks to emulate the performance of larger, teacher models with reduced computational demands. Traditional methods for Large Language Models (LLMs) often necessitate extensive fine-tuning,…

Computation and Language · Computer Science 2025-05-02 Tyler McDonald , Ali Emami

Data-efficient learning has garnered significant attention, especially given the current trend of large multi-modal models. Recently, dataset distillation has become an effective approach by synthesizing data samples that are essential for…

Machine Learning · Computer Science 2024-08-08 Yue Xu , Yong-Lu Li , Kaitong Cui , Ziyu Wang , Cewu Lu , Yu-Wing Tai , Chi-Keung Tang

Knowledge Distillation (KD) aims to transfer knowledge from a large teacher model to a smaller student model. While contrastive learning has shown promise in self-supervised learning by creating discriminative representations, its…

Computer Vision and Pattern Recognition · Computer Science 2025-05-14 Nikolaos Giakoumoglou , Tania Stathaki

Knowledge distillation is an effective way to transfer knowledge from a strong teacher to an efficient student model. Ideally, we expect the better the teacher is, the better the student. However, this expectation does not always come true.…

Information Retrieval · Computer Science 2023-06-27 Zhenghao Lin , Yeyun Gong , Xiao Liu , Hang Zhang , Chen Lin , Anlei Dong , Jian Jiao , Jingwen Lu , Daxin Jiang , Rangan Majumder , Nan Duan

Many natural language processing tasks can be modeled into structured prediction and solved as a search problem. In this paper, we distill an ensemble of multiple models trained with different initialization into a single model. In addition…

Computation and Language · Computer Science 2018-05-30 Yijia Liu , Wanxiang Che , Huaipeng Zhao , Bing Qin , Ting Liu

Recently, Large Language Models (LLMs) have demonstrated significant potential for data annotation, markedly reducing the labor costs associated with downstream applications. However, existing methods mostly adopt an aggressive strategy by…

Machine Learning · Computer Science 2025-06-05 Mingxuan Xia , Haobo Wang , Yixuan Li , Zewei Yu , Jindong Wang , Junbo Zhao , Runze Wu

Distillation enables compact Vision-Language Models (VLMs) to obtain strong reasoning capabilities, yet the prompts driving this process are typically chosen via simple heuristics or aggregated from off-the-shelf datasets. We reveal a…

Machine Learning · Computer Science 2026-05-20 Jaehun Jung , Hyunwoo Kim , Brandon Cui , Ximing Lu , David Acuna , Prithviraj Ammanabrolu , Yejin Choi

Distillation is the technique of training a "student" model based on examples that are labeled by a separate "teacher" model, which itself is trained on a labeled dataset. The most common explanations for why distillation "works" are…

Visuomotor policies often leverage large pre-trained Vision Transformers (ViTs) for their powerful generalization capabilities. However, their significant data requirements present a major challenge in the data-scarce context of most…

Computer Vision and Pattern Recognition · Computer Science 2026-01-19 Maanping Shao , Feihong Zhang , Gu Zhang , Baiye Cheng , Zhengrong Xue , Huazhe Xu

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

Generative Sequential Recommendation (GSR) has emerged as a promising paradigm, reframing recommendation as an autoregressive sequence generation task over discrete Semantic IDs (SIDs), typically derived via codebook-based quantization.…

Information Retrieval · Computer Science 2026-01-26 Dengzhao Fang , Jingtong Gao , Yu Li , Xiangyu Zhao , Yi Chang

Differentiable Architecture Search (DARTS) is a simple yet efficient Neural Architecture Search (NAS) method. During the search stage, DARTS trains a supernet by jointly optimizing architecture parameters and network parameters. During the…

Computer Vision and Pattern Recognition · Computer Science 2023-09-04 Xunyu Zhu , Jian Li , Yong Liu , Weiping Wang

Dataset Distillation (DD) is a prominent technique that encapsulates knowledge from a large-scale original dataset into a small synthetic dataset for efficient training. Meanwhile, Pre-trained Models (PTMs) function as knowledge…

Computer Vision and Pattern Recognition · Computer Science 2023-10-06 Yao Lu , Xuguang Chen , Yuchen Zhang , Jianyang Gu , Tianle Zhang , Yifan Zhang , Xiaoniu Yang , Qi Xuan , Kai Wang , Yang You

Knowledge distillation is considered as a training and compression strategy in which two neural networks, namely a teacher and a student, are coupled together during training. The teacher network is supposed to be a trustworthy predictor…

Computation and Language · Computer Science 2020-12-29 Peyman Passban , Yimeng Wu , Mehdi Rezagholizadeh , Qun Liu

Knowledge distillation (KD) is a widely used framework for training compact, task-specific models by transferring the knowledge from teacher models. However, its application to active learning (AL), which aims to minimize annotation costs…

Machine Learning · Computer Science 2025-10-02 Seongjae Kang , Dong Bok Lee , Hyungjoon Jang , Dongseop Kim , Sung Ju Hwang

Dataset distillation is an effective technique for reducing the cost and complexity of model training while maintaining performance by compressing large datasets into smaller, more efficient versions. In this paper, we present a novel…

Computer Vision and Pattern Recognition · Computer Science 2025-01-09 Longzhen Li , Guang Li , Ren Togo , Keisuke Maeda , Takahiro Ogawa , Miki Haseyama

Diffusion models excel at generative modeling (e.g., text-to-image) but sampling requires multiple denoising network passes, limiting practicality. Efforts such as progressive distillation or consistency distillation have shown promise by…

Machine Learning · Computer Science 2025-04-01 Risheek Garrepalli , Shweta Mahajan , Munawar Hayat , Fatih Porikli

Knowledge distillation (KD) is widely used for compressing a teacher model to a smaller student model, reducing its inference cost and memory footprint while preserving model capabilities. However, current KD methods for auto-regressive…

Computation and Language · Computer Science 2024-07-04 Jongwoo Ko , Sungnyun Kim , Tianyi Chen , Se-Young Yun

Deep models are susceptible to learning spurious correlations, even during the post-processing. We take a closer look at the knowledge distillation -- a popular post-processing technique for model compression -- and find that distilling…

Machine Learning · Computer Science 2023-02-23 Jiwoon Lee , Jaeho Lee