1 code implementation • 4 Jan 2025 • Yutao Jiang, Qiong Wu, Wenhao Lin, Wei Yu, Yiyi Zhou
Recent Multimodal Large Language Models(MLLMs) often use a large number of visual tokens to compensate their visual shortcoming, leading to excessive computation and obvious visual redundancy.
no code implementations • 9 Sep 2024 • Shuai Wang, Yibing Zhan, Yong Luo, Han Hu, Wei Yu, Yonggang Wen, DaCheng Tao
This mechanism assigns different weights to different categories of data according to the gradient of the output score, and uses knowledge distillation (KD) to reduce the mutual interference between the outputs of old and new tasks.
no code implementations • 9 Sep 2024 • Shuai Wang, Liang Ding, Li Shen, Yong Luo, Zheng He, Wei Yu, DaCheng Tao
Then, we selectively eliminate output noise induced by lame prompts based on the uncertainty of the prediction distribution from the standard prompt.
no code implementations • 27 Jun 2024 • Yinghan Li, Wei Yu
This letter investigates an uplink pilot-based wireless indoor localization problem in a multipath environment for a single-input single-output (SISO) narrowband communication system aided by reconfigurable intelligent surface (RIS).
no code implementations • 15 Jun 2024 • Ying Fu, Yu Li, ShaoDi You, Boxin Shi, Linwei Chen, Yunhao Zou, Zichun Wang, Yichen Li, Yuze Han, Yingkai Zhang, Jianan Wang, Qinglin Liu, Wei Yu, Xiaoqian Lv, Jianing Li, Shengping Zhang, Xiangyang Ji, Yuanpei Chen, Yuhan Zhang, Weihang Peng, Liwen Zhang, Zhe Xu, Dingyong Gou, Cong Li, Senyan Xu, Yunkang Zhang, Siyuan Jiang, Xiaoqiang Lu, Licheng Jiao, Fang Liu, Xu Liu, Lingling Li, Wenping Ma, Shuyuan Yang, Haiyang Xie, Jian Zhao, Shihua Huang, Peng Cheng, Xi Shen, Zheng Wang, Shuai An, Caizhi Zhu, Xuelong Li, Tao Zhang, Liang Li, Yu Liu, Chenggang Yan, Gengchen Zhang, Linyan Jiang, Bingyi Song, Zhuoyu An, Haibo Lei, Qing Luo, Jie Song, YuAn Liu, Haoyuan Zhang, Lingfeng Wang, Wei Chen, Aling Luo, Cheng Li, Jun Cao, Shu Chen, Zifei Dou, Xinyu Liu, Jing Zhang, Kexin Zhang, Yuting Yang, Xuejian Gou, Qinliang Wang, Yang Liu, Shizhan Zhao, Yanzhao Zhang, Libo Yan, Yuwei Guo, Guoxin Li, Qiong Gao, Chenyue Che, Long Sun, Xiang Chen, Hao Li, Jinshan Pan, Chuanlong Xie, Hongming Chen, Mingrui Li, Tianchen Deng, Jingwei Huang, Yufeng Li, Fei Wan, Bingxin Xu, Jian Cheng, Hongzhe Liu, Cheng Xu, Yuxiang Zou, Weiguo Pan, Songyin Dai, Sen Jia, Junpei Zhang, Puhua Chen, Qihang Li
The intersection of physics-based vision and deep learning presents an exciting frontier for advancing computer vision technologies.
1 code implementation • 8 May 2024 • Yaqi Wu, Zhihao Fan, Xiaofeng Chu, Jimmy S. Ren, Xiaoming Li, Zongsheng Yue, Chongyi Li, Shangcheng Zhou, Ruicheng Feng, Yuekun Dai, Peiqing Yang, Chen Change Loy, Senyan Xu, Zhijing Sun, Jiaying Zhu, Yurui Zhu, Xueyang Fu, Zheng-Jun Zha, Jun Cao, Cheng Li, Shu Chen, Liang Ma, Shiyang Zhou, Haijin Zeng, Kai Feng, Yongyong Chen, Jingyong Su, Xianyu Guan, Hongyuan Yu, Cheng Wan, Jiamin Lin, Binnan Han, Yajun Zou, Zhuoyuan Wu, Yuan Huang, Yongsheng Yu, Daoan Zhang, Jizhe Li, Xuanwu Yin, Kunlong Zuo, Yunfan Lu, Yijie Xu, Wenzong Ma, Weiyu Guo, Hui Xiong, Wei Yu, Bingchun Luo, Sabari Nathan, Priya Kansal
The increasing demand for computational photography and imaging on mobile platforms has led to the widespread development and integration of advanced image sensors with novel algorithms in camera systems.
no code implementations • 6 May 2024 • Han Han, Tao Jiang, Wei Yu
Specifically, the mobile UEs send uplink pilots to the AP periodically during the channel sensing intervals, the AP then adaptively configures the beamformers and the RIS reflection coefficients for subsequent data transmission based on the received pilots.
no code implementations • 22 Apr 2024 • Juncheng Yang, Zuchao Li, Shuai Xie, Wei Yu, Shijun Li
Domain generalization faces challenges due to the distribution shift between training and testing sets, and the presence of unseen target domains.
no code implementations • 19 Apr 2024 • Juncheng Yang, Zuchao Li, Shuai Xie, WeiPing Zhu, Wei Yu, Shijun Li
While some methods overcome the need for training by leveraging image modality cache and retrieval, they overlook the text modality's importance and cross-modal cues for the efficient adaptation of parameters in visual-language models.
1 code implementation • 18 Apr 2024 • WenHao Zhang, Jun Wang, Yong Luo, Lei Yu, Wei Yu, Zheng He, Jialie Shen
Then we design a spatio-temporal fusion module based on temporal granularity alignment, where the global spatial features extracted from event frames, together with the local relative spatial and temporal features contained in voxel graph list are effectively aligned and integrated.
1 code implementation • 6 Apr 2024 • Juncheng Yang, Zuchao Li, Shuai Xie, Wei Yu, Shijun Li, Bo Du
It is a step-by-step linear reasoning process that adjusts the length of the chain to improve the performance of generated prompts.
1 code implementation • 31 Mar 2024 • Wei Cui, Wei Yu
In most applications of utilizing neural networks for mathematical optimization, a dedicated model is trained for each specific optimization objective.
1 code implementation • 28 Feb 2024 • Qinglin Liu, Xiaoqian Lv, Wei Yu, Changyong Guo, Shengping Zhang
However, existing matting methods are designed for specific objects or guidance, neglecting the common requirement of aggregating global and local contexts in image matting.
Ranked #3 on
Image Matting
on Distinctions-646
no code implementations • 19 Feb 2024 • Muhammad Sohaib, Sang-Woon Jeon, Wei Yu
We consider a multi-user multi-server mobile edge computing (MEC) system, in which users arrive on a network randomly over time and generate computation tasks, which will be computed either locally on their own computing devices or be offloaded to one of the MEC servers.
no code implementations • 22 Jan 2024 • Sadaf Salehkalaibar, Jun Chen, Ashish Khisti, Wei Yu
We derive the RDP function for vector Gaussian sources and propose a waterfilling type solution.
1 code implementation • CVPR 2024 • Wei Yu, Jie Huang, Bing Li, Kaiwen Zheng, Qi Zhu, Man Zhou, Feng Zhao
At the second stage the image-wise compensatory information is derived with the compensatory kernels and embedded into the rescaled input images.
no code implementations • 14 Dec 2023 • Zhongze Zhang, Tao Jiang, Wei Yu
A final DNN is used to map the state vector to the estimated user position.
no code implementations • 13 Dec 2023 • Xiang Wei, Alan J. X. Guo, Sihan Sun, Mengyi Wei, Wei Yu
Under this embedding dimension, the Poisson regression is introduced by assuming the Levenshtein distance between sequences of fixed length following a Poisson distribution, which naturally aligns with the definition of Levenshtein distance.
1 code implementation • 8 Nov 2023 • Zepeng Zhang, Ziping Zhao, Kaiming Shen, Daniel P. Palomar, Wei Yu
By probing the theoretical underpinnings linking the BCA and MM algorithmic frameworks, we reveal the direct correlations between the equivalent transformation techniques, essential to the development of WMMSE and WSR-FP, and the surrogate functions pivotal to WSR-MM.
no code implementations • 19 Oct 2023 • Zhongze Zhang, Tao Jiang, Wei Yu
After all the measurements have been received, a final DNN can be used to map the LSTM cell state to the estimated user equipment (UE) position.
1 code implementation • NeurIPS 2023 • Qiong Wu, Wei Yu, Yiyi Zhou, Shubin Huang, Xiaoshuai Sun, Rongrong Ji
In this paper, we aim at parameter and computation efficient transfer learning (PCETL) for VLP models.
1 code implementation • 11 Jul 2023 • Wei Cui, Wei Yu
In this paper, we recognize the prevalence of non-cumulative objectives in various problems, and propose a modification to existing algorithms for optimizing such objectives.
no code implementations • 2 Jul 2023 • Meng Lan, Fu Rong, Zuchao Li, Wei Yu, Lefei Zhang
Moreover, a bidirectional vision-language interaction module is implemented before the multimodal Transformer to enhance the correlation between the visual and linguistic features, thus facilitating the language queries to decode more precise object information from visual features and ultimately improving the segmentation performance.
no code implementations • 26 Feb 2023 • Wei Yu, Kuiyuan Yang, Yalong Bai, Hongxun Yao, Yong Rui
The image and query are mapped to a common vector space via these two parts respectively, and image-query similarity is naturally defined as an inner product of their mappings in the space.
no code implementations • 23 Feb 2023 • Wei Cui, Wei Yu
This paper proposes a paradigm of uncertainty injection for training deep learning model to solve robust optimization problems.
no code implementations • 7 Oct 2022 • Maria Attarian, Advaya Gupta, Ziyi Zhou, Wei Yu, Igor Gilitschenski, Animesh Garg
Cognitive planning is the structural decomposition of complex tasks into a sequence of future behaviors.
no code implementations • 12 May 2022 • Zhongze Zhang, Tao Jiang, Wei Yu
Reconfigurable intelligent surface (RIS) is capable of intelligently manipulating the phases of the incident electromagnetic wave to improve the wireless propagation environment between the base-station (BS) and the users.
1 code implementation • 8 Dec 2021 • Foad Sohrabi, Tao Jiang, Wei Cui, Wei Yu
This paper proposes a deep learning approach to a class of active sensing problems in wireless communications in which an agent sequentially interacts with an environment over a predetermined number of time frames to gather information in order to perform a sensing or actuation task for maximizing some utility function.
no code implementations • 3 Dec 2021 • Shuai Shao, Lei Xing, Wei Yu, Rui Xu, Yanjiang Wang, BaoDi Liu
Inspired by the concept of self-supervised learning (e. g., setting the pretext task to generate a universal model for the downstream task), we propose a Self-Supervised Dictionary Learning (SSDL) framework to address this challenge.
no code implementations • 27 Apr 2021 • Ziyue Wang, Ya-Feng Liu, Zhilin Chen, Wei Yu
Specifically, at each iteration, the proposed active set CD algorithm first selects a small subset of all devices, namely the active set, which contains a few devices that contribute the most to the deviation from the first-order optimality condition of the MLE problem thus potentially can provide the most improvement to the objective function, then applies the CD algorithm to perform the detection for the devices in the active set.
no code implementations • 10 Apr 2021 • Clym Stock-Williams, Tinkle Chugh, Alma Rahat, Wei Yu
Performing multi-objective Bayesian optimisation by scalarising the objectives avoids the computation of expensive multi-dimensional integral-based acquisition functions, instead of allowing one-dimensional standard acquisition functions\textemdash such as Expected Improvement\textemdash to be applied.
no code implementations • 6 Feb 2021 • Ziyue Wang, Zhilin Chen, Ya-Feng Liu, Foad Sohrabi, Wei Yu
Specifically, at each iteration, the proposed algorithm focuses on only a small subset of all potential sequences, namely the active set, which contains a few most likely active sequences (i. e., transmitted sequences by all active devices), and performs the detection for the sequences in the active set.
no code implementations • 22 Dec 2020 • Wei Cui, Wei Yu
This paper proposes a novel scalable reinforcement learning approach for simultaneous routing and spectrum access in wireless ad-hoc networks.
no code implementations • CVPR 2022 • Wei Yu, Wenxin Chen, Songhenh Yin, Steve Easterbrook, Animesh Garg
Recent works in video prediction have mainly focused on passive forecasting and low-level action-conditional prediction, which sidesteps the learning of interaction between agents and objects.
1 code implementation • 30 Sep 2020 • Tao Jiang, Hei Victor Cheng, Wei Yu
Intelligent reflecting surface (IRS), which consists of a large number of tunable reflective elements, is capable of enhancing the wireless propagation environment in a cellular network by intelligently reflecting the electromagnetic waves from the base-station (BS) toward the users.
no code implementations • 28 Sep 2020 • Wei Yu, Wenxin Chen, Animesh Garg
Recent works in self-supervised video prediction have mainly focused on passive forecasting and low-level action-conditional prediction, which sidesteps the problem of semantic learning.
no code implementations • 27 Sep 2020 • Hiroki Iimori, Takumi Takahashi, Koji Ishibashi, Giuseppe Thadeu Freitas de Abreu, Wei Yu
We propose a novel joint activity, channel, and data estimation (JACDE) scheme for cell-free multiple-input multiple-output (MIMO) systems compliant with fifth-generation (5G) new radio (NR) orthogonal frequency-division multiplexing (OFDM) signaling.
1 code implementation • 24 Aug 2020 • Yalong Bai, Yuxiang Chen, Wei Yu, Linfang Wang, Wei zhang
With the rapid development of electronic commerce, the way of shopping has experienced a revolutionary evolution.
2 code implementations • 13 Jul 2020 • Foad Sohrabi, Kareem M. Attiah, Wei Yu
This paper shows that deep neural network (DNN) can be used for efficient and distributed channel estimation, quantization, feedback, and downlink multiuser precoding for a frequency-division duplex massive multiple-input multiple-output system in which a base station (BS) serves multiple mobile users, but with rate-limited feedback from the users to the BS.
Information Theory Signal Processing Information Theory
no code implementations • 16 Jun 2020 • Mohamed Sana, Antonio De Domenico, Wei Yu, Yves Lostanlen, Emilio Calvanese Strinati
Network densification and millimeter-wave technologies are key enablers to fulfill the capacity and data rate requirements of the fifth generation (5G) of mobile networks.
Multi-agent Reinforcement Learning
reinforcement-learning
+1
1 code implementation • ICLR 2020 • Wei Yu, Yichao Lu, Steve Easterbrook, Sanja Fidler
Applying resolution-preserving blocks is a common practice to maximize information preservation in video prediction, yet their high memory consumption greatly limits their application scenarios.
Ranked #15 on
Video Prediction
on Moving MNIST
no code implementations • 8 Mar 2020 • Shuo Yang, Wei Yu, Ying Zheng, Hongxun Yao, Tao Mei
To solve this new problem, we propose a hierarchical adaptive semantic-visual tree (ASVT) to depict the architecture of merchandise categories, which evaluates semantic similarities between different semantic levels and visual similarities within the same semantic class simultaneously.
no code implementations • 12 Jan 2020 • Shuchao Jiang, Xiaojun Yuan, Xin Wang, Chongbin Xu, Wei Yu
To address the problem that the exact calculation of the messages exchanged within CSCE and between the two modules is complicated due to phase ambiguity issues, this paper proposes a rotationally invariant Gaussian mixture (RIGM) model, and develops an efficient JUICESD-RIGM algorithm.
no code implementations • 8 Dec 2019 • Jie Chen, Ying-Chang Liang, Hei Victor Cheng, Wei Yu
Specifically, we propose a novel channel estimation protocol for the above system to estimate the cascaded channels, which are the products of the channels from the base station (BS) to the RIS and from the RIS to the users.
no code implementations • 25 Oct 2019 • Wei Yu, Yichao Lu, Steve Easterbrook, Sanja Fidler
Applying resolution-preserving blocks is a common practice to maximize information preservation in video prediction, yet their high memory consumption greatly limits their application scenarios.
no code implementations • 29 Jul 2019 • Kai Yang, Yuanming Shi, Wei Yu, Zhi Ding
Edge machine learning can deliver low-latency and private artificial intelligent (AI) services for mobile devices by leveraging computation and storage resources at the network edge.
no code implementations • 16 Jun 2019 • Soukayna Mouatadid, Pierre Gentine, Wei Yu, Steve Easterbrook
Climate projections suffer from uncertain equilibrium climate sensitivity.
1 code implementation • 4 Aug 2018 • Wei Cui, Kaiming Shen, Wei Yu
The optimal scheduling of interfering links in a dense wireless network with full frequency reuse is a challenging task.
1 code implementation • 26 Jul 2018 • Fei Liang, Cong Shen, Wei Yu, Feng Wu
A deep neural network (DNN) based power control method is proposed, which aims at solving the non-convex optimization problem of maximizing the sum rate of a multi-user interference channel.
no code implementations • 4 Nov 2017 • Xurui Li, Wei Yu, Tianyu Luwang, Jianbin Zheng, Xuetao Qiu, Jintao Zhao, Lei Xia, Yujiao Li
Rapid growth of modern technologies such as internet and mobile computing are bringing dramatically increased e-commerce payments, as well as the explosion in transaction fraud.
no code implementations • ICCV 2017 • Stefan Heber, Wei Yu, Thomas Pock
In the first part the network encodes relevant information from the given input into a set of high-level feature maps.
no code implementations • Scientia Marina 2016 • Jintao Wang, Wei Yu, Xinjun Chen, Yong Chen
Because this squid has a short lifespan and is an ecological opportunist, the dynamics of its stock is greatly influenced by the environmental conditions, which need to be considered in its assessment and management.
3 code implementations • CVPR 2015 • Yunjin Chen, Wei Yu, Thomas Pock
We propose to train the parameters of the filters and the influence functions through a loss based approach.
no code implementations • 20 Dec 2014 • Wei Yu, Kuiyuan Yang, Yalong Bai, Hongxun Yao, Yong Rui
Convolutional Neural Networks (CNNs) have achieved comparable error rates to well-trained human on ILSVRC2014 image classification task.
no code implementations • 17 Dec 2013 • Yalong Bai, Kuiyuan Yang, Wei Yu, Wei-Ying Ma, Tiejun Zhao
Image retrieval refers to finding relevant images from an image database for a query, which is considered difficult for the gap between low-level representation of images and high-level representation of queries.
no code implementations • 18 May 2013 • Wei Yu, Junpeng Chen
Based on integrated infrastructure of resource sharing and computing in distributed environment, cloud computing involves the provision of dynamically scalable and provides virtualized resources as services over the Internet.