Search Results for author: Hongyu Li

Found 49 papers, 12 papers with code

\textrm{DuReader}_{\textrm{vis}}: A Chinese Dataset for Open-domain Document Visual Question Answering

1 code implementation Findings (ACL) 2022 Le Qi, Shangwen Lv, Hongyu Li, Jing Liu, Yu Zhang, Qiaoqiao She, Hua Wu, Haifeng Wang, Ting Liu

Open-domain question answering has been used in a wide range of applications, such as web search and enterprise search, which usually takes clean texts extracted from various formats of documents (e. g., web pages, PDFs, or Word documents) as the information source.

document understanding Open-Domain Question Answering +1

Revisiting Catastrophic Forgetting in Large Language Model Tuning

1 code implementation7 Jun 2024 Hongyu Li, Liang Ding, Meng Fang, DaCheng Tao

Catastrophic Forgetting (CF) means models forgetting previously acquired knowledge when learning new data.

Language Modelling Large Language Model

Massive MIMO-ISAC System With 1-Bit ADCs/DACs

no code implementations24 May 2024 Bowen Wang, Hongyu Li, Bin Liao, Ziyang Cheng

This paper investigates a hardware-efficient massive multiple-input multiple-output integrated sensing and communication (MIMO-ISAC) system with 1-bit analog-to-digital converters (ADCs)/digital-to-analog converters (DACs).


Channel Estimation and Beamforming for Beyond Diagonal Reconfigurable Intelligent Surfaces

no code implementations26 Mar 2024 Hongyu Li, Shanpu Shen, Yumeng Zhang, Bruno Clerckx

In this paper, we study channel estimation and beamforming design for BD-RIS aided multi-antenna systems.

V2X-PC: Vehicle-to-everything Collaborative Perception via Point Cluster

no code implementations25 Mar 2024 Si Liu, Zihan Ding, Jiahui Fu, Hongyu Li, Siheng Chen, Shifeng Zhang, Xu Zhou

The point cluster inherently preserves object information while packing messages, with weak relevance to the collaboration range, and supports explicit structure modeling.


ODTFormer: Efficient Obstacle Detection and Tracking with Stereo Cameras Based on Transformer

no code implementations21 Mar 2024 Tianye Ding, Hongyu Li, Huaizu Jiang

In this paper, we propose ODTFormer, a Transformer-based model to address both obstacle detection and tracking problems.

Autonomous Navigation

On the locality of local neural operator in learning fluid dynamics

1 code implementation15 Dec 2023 Ximeng Ye, Hongyu Li, Jingjie Huang, Guoliang Qin

This paper launches a thorough discussion on the locality of local neural operator (LNO), which is the core that enables LNO great flexibility on varied computational domains in solving transient partial differential equations (PDEs).

Beyond Diagonal Reconfigurable Intelligent Surfaces with Mutual Coupling: Modeling and Optimization

no code implementations4 Oct 2023 Hongyu Li, Shanpu Shen, Matteo Nerini, Marco Di Renzo, Bruno Clerckx

This work studies the modeling and optimization of beyond diagonal reconfigurable intelligent surface (BD-RIS) aided wireless communication systems in the presence of mutual coupling among the RIS elements.

ViHOPE: Visuotactile In-Hand Object 6D Pose Estimation with Shape Completion

no code implementations11 Sep 2023 Hongyu Li, Snehal Dikhale, Soshi Iba, Nawid Jamali

By explicitly completing the shape of the in-hand object and jointly optimizing the shape completion and pose estimation tasks, we improve the accuracy of the 6D object pose estimate.

6D Pose Estimation Generative Adversarial Network +1

Channel Estimation for Beyond Diagonal Reconfigurable Intelligent Surfaces with Group-Connected Architectures

no code implementations12 Jul 2023 Hongyu Li, Yumeng Zhang, Bruno Clerckx

We study channel estimation for a beyond diagonal reconfigurable intelligent surface (BD-RIS) aided multiple input single output system.

Reconfigurable Intelligent Surfaces 2.0: Beyond Diagonal Phase Shift Matrices

no code implementations9 Jan 2023 Hongyu Li, Shanpu Shen, Matteo Nerini, Bruno Clerckx

Reconfigurable intelligent surface (RIS) has been envisioned as a promising technique to enable and enhance future wireless communications due to its potential to engineer the wireless channels in a cost-effective manner.

A Dual-Function Radar-Communication System Empowered by Beyond Diagonal Reconfigurable Intelligent Surface

no code implementations9 Jan 2023 Bowen Wang, Hongyu Li, Shanpu Shen, Ziyang Cheng, Bruno Clerckx

This work focuses on the use of reconfigurable intelligent surface (RIS) in dual-function radar-communication (DFRC) systems to improve communication capacity and sensing precision, and enhance coverage for both functions.

Joint Transmit and Receive Beamforming Design in Full-Duplex Integrated Sensing and Communications

no code implementations19 Oct 2022 Ziang Liu, Sundar Aditya, Hongyu Li, Bruno Clerckx

Integrated sensing and communication (ISAC) has been envisioned as a solution to realize the sensing capability required for emerging applications in wireless networks, while efficiently utilizing the available spectral, hardware and energy resources.

A Dynamic Grouping Strategy for Beyond Diagonal Reconfigurable Intelligent Surfaces with Hybrid Transmitting and Reflecting Mode

no code implementations5 Oct 2022 Hongyu Li, Shanpu Shen, Bruno Clerckx

Beyond diagonal reconfigurable intelligent surface (BD-RIS) is a novel branch of RIS which breaks through the limitation of traditional RIS with diagonal scattering matrices.

Dynamic Hybrid Beamforming Design for Dual-Function Radar-Communication Systems

no code implementations11 Sep 2022 Bowen Wang, Hongyu Li, Ziyang Cheng

This paper investigates dynamic hybrid beamforming (HBF) for a dual-function radar-communication (DFRC) system, where the DFRC base station (BS) simultaneously serves multiple single-antenna users and senses a target in the presence of multiple clutters.

Beyond Diagonal Reconfigurable Intelligent Surfaces: A Multi-Sector Mode Enabling Highly Directional Full-Space Wireless Coverage

no code implementations1 Sep 2022 Hongyu Li, Shanpu Shen, Bruno Clerckx

With the proposed model, we first derive the scaling law of the received signal power for a multi-sector BD-RIS-assisted single-user system.

Learning to Learn to Predict Performance Regressions in Production at Meta

no code implementations8 Aug 2022 Moritz Beller, Hongyu Li, Vivek Nair, Vijayaraghavan Murali, Imad Ahmad, Jürgen Cito, Drew Carlson, Ari Aye, Wes Dyer

Catching and attributing code change-induced performance regressions in production is hard; predicting them beforehand, even harder.

counterfactual regression

Vi-Fi: Associating Moving Subjects across Vision and Wireless Sensors

1 code implementation ACM/IEEE International Conference on Information Processing in Sensor Networks (IPSN) 2022 Hansi Liu, Abrar Alali, Mohamed Ibrahim, Bryan Bo Cao, Nicholas Meegan, Hongyu Li, Marco Gruteser, Shubham Jain, Kristin Dana, Ashwin Ashok, Bin Cheng, HongSheng Lu

In this paper, we present Vi-Fi, a multi-modal system that leverages a user’s smartphone WiFi Fine Timing Measurements (FTM) and inertial measurement unit (IMU) sensor data to associate the user detected on a camera footage with their corresponding smartphone identifier (e. g. WiFi MAC address).

Graph Matching Multimodal Association

Deep Learning Eliminates Massive Dust Storms from Images of Tianwen-1

no code implementations21 Jun 2022 Hongyu Li, Jia Li, Xin Ren, Long Xu

Inspired by the haze formation process on Earth, we formulate a similar visual degradation process on clean images and synthesize dusty images sharing a similar feature distribution with realistic dusty images.

Image Dehazing

Rate-Splitting Multiple Access for 6G -- Part III: Interplay with Reconfigurable Intelligent Surfaces

no code implementations4 May 2022 Hongyu Li, Yijie Mao, Onur Dizdar, Bruno Clerckx

This letter is the third part of a three-part tutorial that focuses on rate-splitting multiple access (RSMA) for 6G.

Deep Learning based Intelligent Coin-tap Test for Defect Recognition

1 code implementation20 Mar 2022 Hongyu Li, Peng Jiang, Tiejun Wang

This paper further develops transfer learning strategies for this issue, that is, to transfer the model trained on data of one scenario to another.

Domain Adaptation Pseudo Label +1

Local neural operator for solving transient partial differential equations on varied domains

1 code implementation11 Mar 2022 Hongyu Li, Ximeng Ye, Peng Jiang, Guoliang Qin, Tiejun Wang

For demonstration, LNO learns Navier-Stokes equations from randomly generated data samples, and then the pre-trained LNO is used as an explicit numerical time-marching scheme to solve the flow of fluid on unseen domains, e. g., the flow in a lid-driven cavity and the flow across the cascade of airfoils.

Complementary Feature Enhanced Network with Vision Transformer for Image Dehazing

1 code implementation15 Sep 2021 Dong Zhao, Jia Li, Hongyu Li, Long Xu

In this paper, firstly, we propose a new complementary feature enhanced framework, in which the complementary features are learned by several complementary subtasks and then together serve to boost the performance of the primary task.

Image Dehazing Image Generation +2

Channel Estimation for Practical IRS-Assisted OFDM Systems

no code implementations25 Dec 2020 Wanning Yang, Hongyu Li, Ming Li, Yang Liu, Qian Liu

Different from the prior works which assume that IRS has an ideal reflection model, we perform channel estimation by considering amplitude-phase shift-frequency relationship for the response of practical IRS.

Intelligent reflecting surface enhanced wideband MIMO-OFDM communications: From practical model to reflection optimization

no code implementations26 Jul 2020 Hongyu Li, Wenhao Cai, Yang Liu, Ming Li, Qian Liu, Qingqing Wu

Simulation results demonstrate that the proposed algorithm can offer significant average sum-rate enhancement compared to that achieved using the ideal IRS reflection model, which confirms the importance of the use of the practical model for the design of wideband systems.

A Study on Evaluation Standard for Automatic Crack Detection Regard the Random Fractal

no code implementations23 Jul 2020 Hongyu Li, Jihe Wang, Yu Zhang, Zi-Rui Wang, Tiejun Wang

In CovEval, a different matching process based on the idea of covering box matching is adopted for this issue.

object-detection Object Detection

Practical Modeling and Beamforming for Intelligent Reflecting Surface Aided Wideband Systems

no code implementations2 Jun 2020 Wenhao Cai, Hongyu Li, Ming Li, Qian Liu

In this letter, we aim to investigate the phase-amplitude-frequency relationship of the reflected signals and propose a practical model of reflection coefficient for an IRS-aided wideband system.

Arbitrary-sized Image Training and Residual Kernel Learning: Towards Image Fraud Identification

no code implementations22 May 2020 Hongyu Li, Xiaogang Huang, Zhihui Fu, Xiaolin Li

Preserving original noise residuals in images are critical to image fraud identification.

Knowledge Federation: A Unified and Hierarchical Privacy-Preserving AI Framework

no code implementations5 Feb 2020 Hongyu Li, Dan Meng, Hong Wang, Xiaolin Li

With strict protections and regulations of data privacy and security, conventional machine learning based on centralized datasets is confronted with significant challenges, making artificial intelligence (AI) impractical in many mission-critical and data-sensitive scenarios, such as finance, government, and health.

Federated Learning Privacy Preserving

SuperDTI: Ultrafast diffusion tensor imaging and fiber tractography with deep learning

no code implementations3 Feb 2020 Hongyu Li, Zifei Liang, Chaoyi Zhang, Ruiying Liu, Jing Li, Weihong Zhang, Dong Liang, Bowen Shen, Xiaoliang Zhang, Yulin Ge, Jiangyang Zhang, Leslie Ying

We also demonstrate that the trained neural network is robust to noise and motion in the testing data, and the network trained using healthy volunteer data can be directly applied to stroke patient data without compromising the lesion detectability.

D-NET: A Pre-Training and Fine-Tuning Framework for Improving the Generalization of Machine Reading Comprehension

1 code implementation WS 2019 Hongyu Li, Xiyuan Zhang, Yibing Liu, Yiming Zhang, Quan Wang, Xiangyang Zhou, Jing Liu, Hua Wu, Haifeng Wang

In this paper, we introduce a simple system Baidu submitted for MRQA (Machine Reading for Question Answering) 2019 Shared Task that focused on generalization of machine reading comprehension (MRC) models.

Machine Reading Comprehension Multi-Task Learning +1

Symbol-Level Precoding Design for Intelligent Reflecting Surface Assisted Multi-user MIMO Systems

no code implementations3 Sep 2019 Rang Liu, Hongyu Li, Ming Li, Qian Liu

In this paper we investigate the problem of precoder design for a low-resolution IRS-based transmitter to implement multi-user MISO/MIMO wireless communications.


An End-to-End Encrypted Neural Network for Gradient Updates Transmission in Federated Learning

no code implementations22 Aug 2019 Hongyu Li, Tianqi Han

Federated learning is a distributed learning method to train a shared model by aggregating the locally-computed gradient updates.

Data Compression Federated Learning

Towards Document Image Quality Assessment: A Text Line Based Framework and A Synthetic Text Line Image Dataset

no code implementations5 Jun 2019 Hongyu Li, Fan Zhu, Junhua Qiu

Firstly, since document image quality assessment is more interested in text, we propose a text line based framework to estimate document image quality, which is composed of three stages: text line detection, text line quality prediction, and overall quality assessment.

Image Quality Assessment Line Detection

When Deep Learning Met Code Search

2 code implementations9 May 2019 Jose Cambronero, Hongyu Li, Seohyun Kim, Koushik Sen, Satish Chandra

Our evaluation shows that: 1. adding supervision to an existing unsupervised technique can improve performance, though not necessarily by much; 2. simple networks for supervision can be more effective that more sophisticated sequence-based networks for code search; 3. while it is common to use docstrings to carry out supervision, there is a sizeable gap between the effectiveness of docstrings and a more query-appropriate supervision corpus.

Code Search Natural Language Queries

Cannot find the paper you are looking for? You can Submit a new open access paper.