no code implementations • 26 May 2024 • Zheng Wang, Shu Xian Teo, Jieer Ouyang, Yongjun Xu, Wei Shi
Retrieval-Augmented Generation (RAG) enhances Large Language Models (LLMs) by retrieving relevant memories from an external database.
no code implementations • 28 Apr 2024 • Jiangjie Chen, Xintao Wang, Rui Xu, Siyu Yuan, Yikai Zhang, Wei Shi, Jian Xie, Shuang Li, Ruihan Yang, Tinghui Zhu, Aili Chen, Nianqi Li, Lida Chen, Caiyu Hu, Siye Wu, Scott Ren, Ziquan Fu, Yanghua Xiao
Through this work, we aim to establish a clear taxonomy of RPLA research and applications, and facilitate future research in this critical and ever-evolving field, and pave the way for a future where humans and RPLAs coexist in harmony.
no code implementations • 19 Apr 2024 • Jingqun Tang, Chunhui Lin, Zhen Zhao, Shu Wei, Binghong Wu, Qi Liu, Hao Feng, Yang Li, Siqi Wang, Lei Liao, Wei Shi, Yuliang Liu, Hao liu, Yuan Xie, Xiang Bai, Can Huang
Text-centric visual question answering (VQA) has made great strides with the development of Multimodal Large Language Models (MLLMs), yet open-source models still fall short of leading models like GPT4V and Gemini, partly due to a lack of extensive, high-quality instruction tuning data.
no code implementations • 9 Apr 2024 • Xintao Wang, Jiangjie Chen, Nianqi Li, Lida Chen, Xinfeng Yuan, Wei Shi, Xuyang Ge, Rui Xu, Yanghua Xiao
In the rapidly advancing research fields such as AI, managing and staying abreast of the latest scientific literature has become a significant challenge for researchers.
no code implementations • 7 Feb 2024 • Zheng Wang, Bingzheng Gan, Wei Shi
In this paper, we introduce a novel Multimodal Query Suggestion (MMQS) task, which aims to generate query suggestions based on user query images to improve the intentionality and diversity of search results.
no code implementations • 6 Feb 2024 • Amir Omidi, Mai Banawan, Erwan Weckenmann, Benoit Paquin, Alireza Geravand, Zibo Zheng, Wei Shi, Ming Zeng, Leslie A. Rusch
We present an experimental validation of 4 dB improvement of an ASE-limited PAM4 at 60 Gbaud using an optimized constellation and a NN decoder.
no code implementations • 25 Aug 2023 • Tianyi Zhang, Zheng Wang, Jing Huang, Mohiuddin Muhammad Tasnim, Wei Shi
Fortunately, the availability of open-source stable diffusion models and their underlying mathematical principles has enabled the academic community to extensively analyze the performance of current image generation models and make improvements based on this stable diffusion framework.
no code implementations • 25 Jul 2023 • Wei Shi, Milad Ganjalizadeh, Hossein Shokri Ghadikolaei, Marina Petrova
However, with conventional RL methods, the decision variables (though being deployed at various network layers) are typically optimized in the same control loop, leading to significant practical limitations on the control loop's delay as well as excessive signaling and energy consumption.
Hierarchical Reinforcement Learning reinforcement-learning +1
no code implementations • 8 Jul 2023 • Amanda Dy, Ngoc-Nhu Jennifer Nguyen, Seyed Hossein Mirjahanmardi, Melanie Dawe, Anthony Fyles, Wei Shi, Fei-Fei Liu, Dimitrios Androutsos, Susan Done, April Khademi
This is a critical challenge for clinical translation, as models are typically trained using data available to the vendor, which is not from the target domain.
1 code implementation • 10 May 2023 • Jiangjie Chen, Wei Shi, Ziquan Fu, Sijie Cheng, Lei LI, Yanghua Xiao
Large language models (LLMs) have been widely studied for their ability to store and utilize positive knowledge.
no code implementations • 15 Mar 2023 • Tao Liu, Zhi Wang, Hui He, Liangliang Lin, Wei Shi, Ran An, Chenhao Li
Experiments show that under different Non-IID experiment settings, our method can reduce the upload communication cost to about 2. 9% to 18. 9% of the conventional federated learning algorithm when the sparse rate is 0. 01.
no code implementations • 9 Feb 2023 • Ahmet M. Elbir, Wei Shi, Anastasios K. Papazafeiropoulos, Pandelis Kourtessis, Symeon Chatzinotas
Unlike prior works which mostly ignore the impact of near-field beam-split (NB) and consider either narrowband scenario or far-field models, this paper introduces both a model-based and a model-free techniques for wideband THz channel estimation in the presence of NB.
no code implementations • 7 Feb 2023 • Wei Shi, Wentao Zhang, Weishi Zheng, Ruixuan Wang
There is an increasing demand for interpretation of model predictions especially in high-risk applications.
no code implementations • ICCV 2023 • Jianbing Wu, Hong Liu, Yuxin Su, Wei Shi, Hao Tang
Owing to the large distribution gap between the heterogeneous data in Visible-Infrared Person Re-identification (VI Re-ID), we point out that existing paradigms often suffer from the inter-modal semantic misalignment issue and thus fail to align and compare local details properly.
1 code implementation • 25 Aug 2022 • Jianbing Wu, Hong Liu, Wei Shi, Hao Tang, Jingwen Guo
To mitigate the resolution degradation issue and mine identity-sensitive cues from human faces, we propose to restore the missing facial details using prior facial knowledge, which is then propagated to a smaller network.
no code implementations • 7 Aug 2022 • Ahmet M. Elbir, Wei Shi, Anastasios K. Papazafeiropoulos, Pandelis Kourtessis, Symeon Chatzinotas
For the demonstration of ultra-wideband bandwidth and pencil-beamforming, the terahertz (THz)-band has been envisioned as one of the key enabling technologies for the sixth generation networks.
no code implementations • 13 Jul 2022 • Wei Shi, Hanrui Wang, Jiaqi Gu, Mingjie Liu, David Pan, Song Han, Nan Sun
To address the challenge, we present RobustAnalog, a robust circuit design framework that involves the variation information in the optimization process.
no code implementations • 13 Jul 2022 • Ahmet M. Elbir, Wei Shi, Kumar Vijay Mishra, Symeon Chatzinotas
This paper addresses two major challenges in terahertz (THz) channel estimation: the beam-split phenomenon, i. e., beam misalignment because of frequency-independent analog beamformers, and computational complexity because of the usage of ultra-massive number of antennas to compensate propagation losses.
no code implementations • 24 Jun 2022 • Ahmet M. Elbir, Wei Shi, Kumar Vijay Mishra, Anastasios K. Papazafeiropoulos, Symeon Chatzinotas
Without channel estimation, the proposed approach exhibits approximately 60% improvement in image and speech classification tasks for diverse scenarios such as millimeter wave and IEEE 802. 11p vehicular channels.
1 code implementation • 27 Apr 2022 • Junquan Deng, Wei Shi, Jianzhao Zhang, Xianyu Zhang, Chuan Zhang
Similarity metric is crucial for massive MIMO positioning utilizing channel state information~(CSI).
no code implementations • Findings (ACL) 2022 • Jiangjie Chen, Rui Xu, Ziquan Fu, Wei Shi, Zhongqiao Li, Xinbo Zhang, Changzhi Sun, Lei LI, Yanghua Xiao, Hao Zhou
Holding the belief that models capable of reasoning should be right for the right reasons, we propose a first-of-its-kind Explainable Knowledge-intensive Analogical Reasoning benchmark (E-KAR).
1 code implementation • 5 Dec 2021 • Tao Wang, Hong Liu, Pinhao Song, Tianyu Guo, Wei Shi
Therefore, we propose a transformer-based Pose-guided Feature Disentangling (PFD) method by utilizing pose information to clearly disentangle semantic components (e. g. human body or joint parts) and selectively match non-occluded parts correspondingly.
no code implementations • 26 Nov 2021 • Junquan Deng, Wei Shi, Jian Hu, Xianlong Jiao
We consider the mobile localization problem in future millimeter-wave wireless networks with distributed Base Stations (BSs) based on multi-antenna channel state information (CSI).
no code implementations • 10 Nov 2021 • Seyed Hossein Mirjahanmardi, Melanie Dawe, Anthony Fyles, Wei Shi, Fei-Fei Liu, Susan Done, April Khademi
Nuclei detection is a key task in Ki67 proliferation index estimation in breast cancer images.
no code implementations • 29 Sep 2021 • Wei Shi, Hanrui Wang, Jiaqi Gu, Mingjie Liu, David Z. Pan, Song Han, Nan Sun
Specifically, circuit optimizations under different variations are considered as a set of tasks.
1 code implementation • 25 Aug 2021 • Jia-Xin Zhuang, Wanying Tao, Jianfei Xing, Wei Shi, Ruixuan Wang, Wei-Shi Zheng
In this paper, a simple yet effective optimization method is proposed to interpret the activation of any kernel of interest in CNN models.
no code implementations • ACL 2021 • Wei Shi, Vera Demberg
Implicit discourse relation classification is a challenging task, in particular when the text domain is different from the standard Penn Discourse Treebank (PDTB; Prasad et al., 2008) training corpus domain (Wall Street Journal in 1990s).
no code implementations • 12 Feb 2020 • Wei Shi, Si-Yuan Zhang, Zhiwei Zhang, Hong Cheng, Jeffrey Xu Yu
The named entity linking is challenging, given the fact that there are multiple candidate entities for a mention in a document.
no code implementations • IJCNLP 2019 • Wei Shi, Vera Demberg
Implicit discourse relation classification is one of the most difficult tasks in discourse parsing.
no code implementations • WS 2019 • Fangzhou Zhai, Vera Demberg, Pavel Shkadzko, Wei Shi, Asad Sayeed
The model exploits a symbolic text planning module to produce text plans, thus reducing the demand of data; a neural surface realization module then generates fluent text conditioned on the text plan.
1 code implementation • 6 Nov 2018 • Hanrong Ye, Xia Li, Hong Liu, Wei Shi, Mengyuan Liu, Qianru Sun
Rain removal aims to extract and remove rain streaks from images.
no code implementations • WS 2019 • Wei Shi, Vera Demberg
Implicit discourse relation classification is one of the most difficult steps in discourse parsing.
no code implementations • WS 2019 • Wei Shi, Frances Yung, Vera Demberg
Implicit discourse relation classification is one of the most challenging and important tasks in discourse parsing, due to the lack of connective as strong linguistic cues.
1 code implementation • 31 May 2018 • Hoi-To Wai, Wei Shi, Cesar A. Uribe, Angelia Nedich, Anna Scaglione
This paper studies an acceleration technique for incremental aggregated gradient ({\sf IAG}) method through the use of \emph{curvature} information for solving strongly convex finite sum optimization problems.
no code implementations • IJCNLP 2017 • Wei Shi, Frances Yung, Raphael Rubino, Vera Demberg
Implicit discourse relation recognition is an extremely challenging task due to the lack of indicative connectives.
General Classification Implicit Discourse Relation Classification +4
no code implementations • 24 Oct 2017 • Hoi-To Wai, Wei Shi, Angelia Nedic, Anna Scaglione
We propose a new algorithm for finite sum optimization which we call the curvature-aided incremental aggregated gradient (CIAG) method.
no code implementations • 25 Apr 2017 • Zhi Li, Wei Shi, Ming Yan
This paper proposes a novel proximal-gradient algorithm for a decentralized optimization problem with a composite objective containing smooth and non-smooth terms.
no code implementations • EACL 2017 • Wei Shi, Vera Demberg
The task of implicit discourse relation classification has received increased attention in recent years, including two CoNNL shared tasks on the topic.
no code implementations • 19 Sep 2016 • Angelia Nedić, Alex Olshevsky, Wei Shi, César A. Uribe
A recent algorithmic family for distributed optimization, DIGing's, have been shown to have geometric convergence over time-varying undirected/directed graphs.
no code implementations • Circuits, Systems, and Signal Processing volume 35, pages1795–1805 2015 • Jin Sha, Kai Huang, Wei Shi, Zhongfeng Wangzfwang
Multiple signal classification (MUSIC) algorithm is widely used in measuring the direction of arrival.
no code implementations • 24 Apr 2014 • Wei Shi, Qing Ling, Gang Wu, Wotao Yin
In this paper, we develop a decentralized algorithm for the consensus optimization problem $$\min\limits_{x\in\mathbb{R}^p}~\bar{f}(x)=\frac{1}{n}\sum\limits_{i=1}^n f_i(x),$$ which is defined over a connected network of $n$ agents, where each function $f_i$ is held privately by agent $i$ and encodes the agent's data and objective.
Optimization and Control