English
Related papers

Related papers: Breaking the Compression Ceiling: Data-Free Pipeli…

200 papers

In this paper, we propose an ultrafast automated model compression framework called SeerNet for flexible network deployment. Conventional non-differen-tiable methods discretely search the desirable compression policy based on the accuracy…

Computer Vision and Pattern Recognition · Computer Science 2023-04-14 Ziwei Wang , Jiwen Lu , Han Xiao , Shengyu Liu , Jie Zhou

Recent works have indicated redundancy across transformer blocks, prompting the research of depth compression to prune less crucial blocks. However, current ways of entire-block pruning suffer from risks of discarding meaningful cues…

Computer Vision and Pattern Recognition · Computer Science 2026-02-10 Ruihan Xu , Qingpei Guo , Yao Zhu , Xiangyang Ji , Ming Yang , Shiliang Zhang

While Learned Data Compression (LDC) has achieved superior compression ratios, balancing precise probability modeling with system efficiency remains challenging. Crucially, uniform single-stream architectures struggle to simultaneously…

Computation and Language · Computer Science 2026-04-09 Huidong Ma , Xinyan Shi , Hui Sun , Xiaofei Yue , Xiaoguang Liu , Gang Wang , Wentong Cai

With the rapid scaling of neural networks, data storage and communication demands have intensified. Dataset distillation has emerged as a promising solution, condensing information from extensive datasets into a compact set of synthetic…

Computer Vision and Pattern Recognition · Computer Science 2024-12-09 Ali Abbasi , Shima Imani , Chenyang An , Gayathri Mahalingam , Harsh Shrivastava , Maurice Diesendruck , Hamed Pirsiavash , Pramod Sharma , Soheil Kolouri

Despite the success of deep neural networks (DNNs), state-of-the-art models are too large to deploy on low-resource devices or common server configurations in which multiple models are held in memory. Model compression methods address this…

As the volume of data available from sensor-enabled devices such as vehicles expands, it is increasingly hard for companies to make informed decisions about the cost of capturing, processing, and storing the data from every device. Business…

Performance · Computer Science 2025-04-16 Christopher Bogart , Rajeev Chhajer , Baljit Singh , Tony Fontana , Majd Sakr

Diffusion models like Stable Diffusion (SD) drive a vibrant open-source ecosystem including fully fine-tuned checkpoints and parameter-efficient adapters such as LoRA, LyCORIS, and ControlNet. However, these adaptation components are…

Machine Learning · Computer Science 2025-12-04 Zhidong Gao , Zimeng Pan , Yuhang Yao , Chenyue Xie , Wei Wei

From a multi-model compression perspective, model merging enables memory-efficient serving of multiple models fine-tuned from the same base, but suffers from degraded performance due to interference among their task-specific parameter…

Machine Learning · Computer Science 2025-05-19 Hangyu Zhou , Aaron Gokaslan , Volodymyr Kuleshov , Bharath Hariharan

We explore an error-bounded lossy compression approach for reducing scientific data associated with 2D/3D unstructured meshes. While existing lossy compressors offer a high compression ratio with bounded error for regular grid data,…

Graphics · Computer Science 2024-04-04 Congrong Ren , Xin Liang , Hanqi Guo

Large language models (LLMs) rely on pretraining on massive and heterogeneous corpora, where training data composition has a decisive impact on training efficiency and downstream generalization under realistic compute and data budget…

Computation and Language · Computer Science 2026-04-21 Zhuo Chen , Yuxuan Miao , Supryadi , Deyi Xiong

Massive data is often considered essential for deep learning applications, but it also incurs significant computational and infrastructural costs. Therefore, dataset pruning (DP) has emerged as an effective way to improve data efficiency by…

Machine Learning · Computer Science 2023-11-21 Yihua Zhang , Yimeng Zhang , Aochuan Chen , Jinghan Jia , Jiancheng Liu , Gaowen Liu , Mingyi Hong , Shiyu Chang , Sijia Liu

Adapting large pretrained models to diverse tasks is now routine, yet the two dominant strategies of parameter-efficient fine-tuning (PEFT) and low-rank compression are typically composed in sequence. This decoupled practice first…

Artificial Intelligence · Computer Science 2026-05-05 Jingze Ge , Yun Liu , Xue Geng , Wanqi Dong , Wang Zhe Mark , Min Wu , Xulei Yang

Structured pruning is an effective approach for compressing large pre-trained neural networks without significantly affecting their performance. However, most current structured pruning methods do not provide any performance guarantees, and…

Machine Learning · Computer Science 2023-02-14 Marwa El Halabi , Suraj Srinivas , Simon Lacoste-Julien

Large language models (LLM) have achieved remarkable performance across a wide range of tasks. However, their substantial parameter sizes pose significant challenges for deployment on edge devices with limited computational and memory…

Computation and Language · Computer Science 2025-12-16 Yu-Chen Lu , Sheng-Feng Yu , Hui-Hsien Weng , Pei-Shuo Wang , Yu-Fang Hu , Liang Hung-Chun , Hung-Yueh Chiang , Kai-Chiang Wu

Large-scale 3D generative models require substantial computational resources yet often fall short in capturing fine details and complex geometries at high resolutions. We attribute this limitation to the inefficiency of current…

Computer Vision and Pattern Recognition · Computer Science 2024-11-13 Aditya Sanghi , Aliasghar Khani , Pradyumna Reddy , Arianna Rampini , Derek Cheung , Kamal Rahimi Malekshan , Kanika Madan , Hooman Shayani

The recent advances of hardware technology have made the intelligent analysis equipped at the front-end with deep learning more prevailing and practical. To better enable the intelligent sensing at the front-end, instead of compressing and…

Multimedia · Computer Science 2018-09-18 Zhuo Chen , Weisi Lin , Shiqi Wang , Lingyu Duan , Alex C. Kot

The non-uniform distribution and extremely sparse nature of the LiDAR point cloud (LPC) bring significant challenges to its high-efficient compression. This paper proposes a novel end-to-end, fully-factorized deep framework that encodes the…

Computer Vision and Pattern Recognition · Computer Science 2023-02-15 Tingyu Fan , Linyao Gao , Yiling Xu , Dong Wang , Zhu Li

A ubiquitous feature of data of our era is their extra-large sizes and dimensions. Analyzing such high-dimensional data poses significant challenges, since the feature dimension is often much larger than the sample size. This thesis…

Statistics Theory · Mathematics 2025-09-11 Kai Yang

Scaling models has led to significant advancements in deep learning, but training these models in decentralized settings remains challenging due to communication bottlenecks. While existing compression techniques are effective in…

Machine Learning · Computer Science 2025-06-03 Sameera Ramasinghe , Thalaiyasingam Ajanthan , Gil Avraham , Yan Zuo , Alexander Long

Dataset distillation (DD) aims to construct compact synthetic datasets that allow models to achieve comparable performance to full-data training while substantially reducing storage and computation. Despite rapid empirical progress, its…

Machine Learning · Computer Science 2025-12-11 Zhengquan Luo , Zhiqiang Xu
‹ Prev 1 4 5 6 7 8 10 Next ›