English
Related papers

Related papers: Arbitrary Ratio Feature Compression via Next Token…

200 papers

Generative face video coding (GFVC) is vital for modern applications like video conferencing, yet existing methods primarily focus on video motion while neglecting the significant bitrate contribution of audio. Despite the well-established…

Image and Video Processing · Electrical Eng. & Systems 2025-12-18 Youmin Xu , Mengxi Guo , Shijie Zhao , Weiqi Li , Junlin Li , Li Zhang , Jian Zhang

Token compression aims to speed up large-scale vision transformers (e.g. ViTs) by pruning (dropping) or merging tokens. It is an important but challenging task. Although recent advanced approaches achieved great success, they need to…

Computer Vision and Pattern Recognition · Computer Science 2023-05-30 Mengzhao Chen , Wenqi Shao , Peng Xu , Mingbao Lin , Kaipeng Zhang , Fei Chao , Rongrong Ji , Yu Qiao , Ping Luo

The challenges in feature selection, particularly in balancing model accuracy, interpretability, and computational efficiency, remain a critical issue in advancing machine learning methodologies. To address these complexities, this study…

Machine Learning · Computer Science 2026-01-06 Nachiket Kapure , Harsh Joshi , Parul Kumari , Rajeshwari Mistri , Manasi Mali

We study the decentralized consensus and stochastic optimization problems with compressed communications over static directed graphs. We propose an iterative gradient-based algorithm that compresses messages according to a desired…

Optimization and Control · Mathematics 2022-04-19 Mohammad Taha Toghani , César A. Uribe

While fine-tuning is a de facto standard method for training deep neural networks, it still suffers from overfitting when using small target datasets. Previous methods improve fine-tuning performance by maintaining knowledge of the source…

Machine Learning · Computer Science 2024-03-18 Shin'ya Yamaguchi , Sekitoshi Kanai , Kazuki Adachi , Daiki Chijiwa

Feature selection aims to identify the optimal feature subset for enhancing downstream models. Effective feature selection can remove redundant features, save computational resources, accelerate the model learning process, and improve the…

Machine Learning · Computer Science 2024-12-19 Nanxu Gong , Wangyang Ying , Dongjie Wang , Yanjie Fu

We introduce ARPG, a novel visual Autoregressive model that enables Randomized Parallel Generation, addressing the inherent limitations of conventional raster-order approaches, which hinder inference efficiency and zero-shot generalization…

Computer Vision and Pattern Recognition · Computer Science 2026-03-02 Haopeng Li , Jinyue Yang , Guoqi Li , Huan Wang

Video semantic segmentation (VSS) is a computationally expensive task due to the per-frame prediction for videos of high frame rates. In recent work, compact models or adaptive network strategies have been proposed for efficient VSS.…

Computer Vision and Pattern Recognition · Computer Science 2023-03-14 Yubin Hu , Yuze He , Yanghao Li , Jisheng Li , Yuxing Han , Jiangtao Wen , Yong-Jin Liu

Video quality can suffer from limited internet speed while being streamed by users. Compression artifacts start to appear when the bitrate decreases to match the available bandwidth. Existing algorithms either focus on removing the…

Computer Vision and Pattern Recognition · Computer Science 2024-01-29 Wen Ma , Qiuwen Lou , Arman Kazemi , Julian Faraone , Tariq Afzal

Training large language models (LLMs) is often constrained by GPU memory limitations. To alleviate memory pressure, activation recomputation and data compression have been proposed as two major strategies. However, both approaches have…

Machine Learning · Computer Science 2025-08-11 Ping Chen , Zhuohong Deng , Ping Li , Shuibing He , Hongzi Zhu , Yi Zheng , Zhefeng Wang , Baoxing Huai , Minyi Guo

How to model fine-grained spatial-temporal dynamics in videos has been a challenging problem for action recognition. It requires learning deep and rich features with superior distinctiveness for the subtle and abstract motions. Most…

Computer Vision and Pattern Recognition · Computer Science 2021-07-27 Hanxi Lin , Xinxiao Wu , Jiebo Luo

In this paper, we propose a novel accuracy-reconfigurable stochastic computing (ARSC) framework for dynamic reliability and power management. Different than the existing stochastic computing works, where the accuracy versus power/energy…

Hardware Architecture · Computer Science 2020-04-29 Shuyuan Yu , Han Zhou , Shaoyi Peng , Hussam Amrouch , Joerg Henkel , Sheldon X. -D. Tan

In this work we present a new framework for neural networks compression with fine-tuning, which we called Neural Network Compression Framework (NNCF). It leverages recent advances of various network compression methods and implements some…

Computer Vision and Pattern Recognition · Computer Science 2021-01-01 Alexander Kozlov , Ivan Lazarevich , Vasily Shamporov , Nikolay Lyalyushkin , Yury Gorbachev

Video super-resolution (VSR) methods have recently achieved a remarkable success due to the development of deep convolutional neural networks (CNN). Current state-of-the-art CNN methods usually treat the VSR problem as a large number of…

Computer Vision and Pattern Recognition · Computer Science 2020-02-18 Jingwei Xin , Nannan Wang , Jie Li , Xinbo Gao , Zhifeng Li

Fine-tuning is widely applied in image classification tasks as a transfer learning approach. It re-uses the knowledge from a source task to learn and obtain a high performance in target tasks. Fine-tuning is able to alleviate the challenge…

Computer Vision and Pattern Recognition · Computer Science 2022-07-27 Xuyang Shen , Jo Plested , Sabrina Caldwell , Yiran Zhong , Tom Gedeon

Due to the fundamental connection between next-symbol prediction and compression, modern predictive models, such as large language models (LLMs), can be combined with entropy coding to achieve compression rates that surpass those of…

Information Theory · Computer Science 2026-01-27 Cordelia Hu , Jennifer Tang

Coding images for machines with minimal bitrate and strong analysis performance is key to effective edge-cloud systems. Several approaches deploy an image codec and perform analysis on the reconstructed image. Other methods compress…

Computer Vision and Pattern Recognition · Computer Science 2025-09-24 Xinyu Wang , Zikun Zhou , Yingjian Li , Xin An , Hongpeng Wang

This paper introduces xRAG, an innovative context compression method tailored for retrieval-augmented generation. xRAG reinterprets document embeddings in dense retrieval--traditionally used solely for retrieval--as features from the…

Computation and Language · Computer Science 2024-12-10 Xin Cheng , Xun Wang , Xingxing Zhang , Tao Ge , Si-Qing Chen , Furu Wei , Huishuai Zhang , Dongyan Zhao

In this paper, we present a topology optimization (TO) framework to simultaneously optimize the matrix topology and fiber distribution of functionally graded continuous fiber-reinforced composites (FRC). Current approaches in density-based…

Computational Engineering, Finance, and Science · Computer Science 2022-05-16 Aaditya Chandrasekhar , Amir Mirzendehdel , Morad Behandish , Krishnan Suresh

Motion prediction has been studied in different contexts with models trained on narrow distributions and applied to downstream tasks in human motion prediction and robotics. Simultaneously, recent efforts in scaling video prediction have…

Computer Vision and Pattern Recognition · Computer Science 2025-12-30 Johnathan Xie , Stefan Stojanov , Cristobal Eyzaguirre , Daniel L. K. Yamins , Jiajun Wu