English
Related papers

Related papers: Distilling foundation models for robust and effici…

200 papers

Pathology foundation models (PFMs) have enabled robust generalization in computational pathology through large-scale datasets and expansive architectures, but their substantial computational cost, particularly for gigapixel whole slide…

Fine-tuning large models is highly effective, however, inference can be expensive and produces carbon emissions. Knowledge distillation has been shown to be a practical solution to reduce inference costs, but the distillation process itself…

Computation and Language · Computer Science 2023-07-07 Junmo Kang , Wei Xu , Alan Ritter

Diffusion models (DMs) have demonstrated exceptional generative capabilities across various domains, including image, video, and so on. A key factor contributing to their effectiveness is the high quantity and quality of data used during…

Computer Vision and Pattern Recognition · Computer Science 2025-03-03 Qianlong Xiang , Miao Zhang , Yuzhang Shang , Jianlong Wu , Yan Yan , Liqiang Nie

Dataset distillation aims to synthesize small datasets with little information loss from original large-scale ones for reducing storage and training costs. Recent state-of-the-art methods mainly constrain the sample synthesis process by…

Computer Vision and Pattern Recognition · Computer Science 2023-08-31 Yanqing Liu , Jianyang Gu , Kai Wang , Zheng Zhu , Wei Jiang , Yang You

Dataset distillation (DD) is a newly emerging research area aiming at alleviating the heavy computational load in training models on large datasets. It tries to distill a large dataset into a small and condensed one so that models trained…

Computer Vision and Pattern Recognition · Computer Science 2023-11-28 Yuxuan Duan , Jianfu Zhang , Liqing Zhang

Foundation models are rapidly being developed for computational pathology applications. However, it remains an open question which factors are most important for downstream performance with data scale and diversity, model size, and training…

Federated learning is widely used in medical applications for training global models without needing local data access. However, varying computational capabilities and network architectures (system heterogeneity), across clients pose…

Machine Learning · Computer Science 2024-05-14 Luyuan Xie , Manqing Lin , Tianyu Luan , Cong Li , Yuejian Fang , Qingni Shen , Zhonghai Wu

Recent advancements in timestep-distilled diffusion models have enabled high-quality image generation that rivals non-distilled multi-step models, but with significantly fewer inference steps. While such models are attractive for…

Computer Vision and Pattern Recognition · Computer Science 2025-03-04 Zichen Miao , Zhengyuan Yang , Kevin Lin , Ze Wang , Zicheng Liu , Lijuan Wang , Qiang Qiu

Medical foundation models pre-trained on large-scale datasets have shown powerful versatile performance. However, when adapting medical foundation models for specific medical scenarios, it remains the inevitable challenge due to the gap…

Computer Vision and Pattern Recognition · Computer Science 2026-05-07 Siyuan Du , Yuhang Zhou , Haolin Li , Jiangchao Yao , Haishuai Wang , Hui Lin , Ya Zhang , Yanfeng Wang

Self-supervised foundation models have shown great potential in computer vision thanks to the pre-training paradigm of masked autoencoding. Scale is a primary factor influencing the performance of these foundation models. However, these…

Computer Vision and Pattern Recognition · Computer Science 2024-04-02 Zhiyu Zhao , Bingkun Huang , Sen Xing , Gangshan Wu , Yu Qiao , Limin Wang

As the size of pre-trained speech recognition models increases, running these large models in low-latency or resource-constrained environments becomes challenging. In this work, we leverage pseudo-labelling to assemble a large-scale…

Computation and Language · Computer Science 2023-11-02 Sanchit Gandhi , Patrick von Platen , Alexander M. Rush

Data heterogeneity presents significant challenges for federated learning (FL). Recently, dataset distillation techniques have been introduced, and performed at the client level, to attempt to mitigate some of these challenges. In this…

Machine Learning · Computer Science 2023-12-05 Yuqi Jia , Saeed Vahidian , Jingwei Sun , Jianyi Zhang , Vyacheslav Kungurtsev , Neil Zhenqiang Gong , Yiran Chen

In this paper, we study \xw{dataset distillation (DD)}, from a novel perspective and introduce a \emph{dataset factorization} approach, termed \emph{HaBa}, which is a plug-and-play strategy portable to any existing DD baseline. Unlike…

Computer Vision and Pattern Recognition · Computer Science 2022-11-01 Songhua Liu , Kai Wang , Xingyi Yang , Jingwen Ye , Xinchao Wang

Neural networks achieve state-of-the-art performance in many supervised learning tasks when the training data distribution matches the test data distribution. However, their performance drops significantly under domain (covariate) shift, a…

Computer Vision and Pattern Recognition · Computer Science 2024-09-13 Kerem Cekmeceli , Meva Himmetoglu , Guney I. Tombak , Anna Susmelj , Ertunc Erdil , Ender Konukoglu

Diffusion models (DMs) have recently been introduced in image deblurring and exhibited promising performance, particularly in terms of details reconstruction. However, the diffusion model requires a large number of inference iterations to…

Computer Vision and Pattern Recognition · Computer Science 2023-09-26 Zheng Chen , Yulun Zhang , Ding Liu , Bin Xia , Jinjin Gu , Linghe Kong , Xin Yuan

Self-supervised learning (SSL) models like WavLM can be effectively utilized when building speaker diarization systems but are often large and slow, limiting their use in resource constrained scenarios. Previous studies have explored…

Audio and Speech Processing · Electrical Eng. & Systems 2025-06-02 Jiangyu Han , Federico Landini , Johan Rohdin , Anna Silnova , Mireia Diez , Jan Cernocky , Lukas Burget

Deploying artificial intelligence (AI) models on edge devices involves a delicate balance between meeting stringent complexity constraints, such as limited memory and energy resources, and ensuring reliable performance in sensitive…

Machine Learning · Computer Science 2025-10-02 Jiayi Huang , Sangwoo Park , Nicola Paoletti , Osvaldo Simeone

Modeling physical systems in a generative manner offers several advantages, including the ability to handle partial observations, generate diverse solutions, and address both forward and inverse problems. Recently, diffusion models have…

Machine Learning · Computer Science 2025-05-29 Yi Zhang , Difan Zou

In the past year, distillation has seen a renewed prominence in large language model (LLM) pretraining, exemplified by the Llama-3.2 and Gemma model families. While distillation has historically been shown to improve statistical modeling,…

Machine Learning · Computer Science 2025-09-03 Sachin Goyal , David Lopez-Paz , Kartik Ahuja

Large language models (LLMs) excel in complex reasoning tasks, and distilling their reasoning capabilities into smaller models has shown promise. However, we uncover an interesting phenomenon, which we term the Small Model Learnability Gap:…

Artificial Intelligence · Computer Science 2025-11-14 Yuetai Li , Xiang Yue , Zhangchen Xu , Fengqing Jiang , Luyao Niu , Bill Yuchen Lin , Bhaskar Ramasubramanian , Radha Poovendran