Search Results for author: Bing Wang

Found 78 papers, 33 papers with code

UniCoder: Scaling Code Large Language Model via Universal Code

no code implementations24 Jun 2024 Tao Sun, Linzheng Chai, Jian Yang, Yuwei Yin, Hongcheng Guo, Jiaheng Liu, Bing Wang, Liqun Yang, Zhoujun Li

When applying LLMs for code generation, recent works mainly focus on directing the models to articulate intermediate natural-language reasoning steps, as in chain-of-thought (CoT) prompting, and then output code with the natural language or other structured intermediate steps.

Code Translation Language Modelling +2

Revealing the structure-property relationships of copper alloys with FAGC

no code implementations15 Apr 2024 Yuexing Han, Guanxin Wan, Tao Han, Bing Wang, Yi Liu

These outcomes underscore the potential of FAGC to address the challenge of limited image data in materials science, providing a powerful tool for establishing detailed and quantitative relationships between complex microstructures and material properties.

Self-Supervised Multi-Frame Neural Scene Flow

no code implementations24 Mar 2024 Dongrui Liu, Daqi Liu, Xueqian Li, Sihao Lin, Hongwei Xie, Bing Wang, Xiaojun Chang, Lei Chu

Neural Scene Flow Prior (NSFP) and Fast Neural Scene Flow (FNSF) have shown remarkable adaptability in the context of large out-of-distribution autonomous driving.

Autonomous Driving Scene Flow Estimation

Mini-Splatting: Representing Scenes with a Constrained Number of Gaussians

1 code implementation21 Mar 2024 Guangchi Fang, Bing Wang

In this study, we explore the challenge of efficiently representing scenes with a constrained number of Gaussians.


HCPM: Hierarchical Candidates Pruning for Efficient Detector-Free Matching

no code implementations19 Mar 2024 Ying Chen, Yong liu, Kai Wu, Qiang Nie, Shang Xu, Huifang Ma, Bing Wang, Chengjie Wang

Deep learning-based image matching methods play a crucial role in computer vision, yet they often suffer from substantial computational demands.

NeuV-SLAM: Fast Neural Multiresolution Voxel Optimization for RGBD Dense SLAM

no code implementations3 Feb 2024 Wenzhi Guo, Bing Wang, Lijun Chen

We introduce NeuV-SLAM, a novel dense simultaneous localization and mapping pipeline based on neural multiresolution voxels, characterized by ultra-fast convergence and incremental expansion capabilities.

Simultaneous Localization and Mapping

xCoT: Cross-lingual Instruction Tuning for Cross-lingual Chain-of-Thought Reasoning

no code implementations13 Jan 2024 Linzheng Chai, Jian Yang, Tao Sun, Hongcheng Guo, Jiaheng Liu, Bing Wang, Xiannian Liang, Jiaqi Bai, Tongliang Li, Qiyao Peng, Zhoujun Li

To bridge the gap among different languages, we propose a cross-lingual instruction fine-tuning framework (xCOT) to transfer knowledge from high-resource languages to low-resource languages.

Few-Shot Learning Language Modelling +1

Few-shot Image Generation via Information Transfer from the Built Geodesic Surface

no code implementations3 Jan 2024 Yuexing Han, Liheng Ruan, Bing Wang

Images generated by most of generative models trained with limited data often exhibit deficiencies in either fidelity, diversity, or both.

Diversity Image Generation

MAC-SQL: A Multi-Agent Collaborative Framework for Text-to-SQL

1 code implementation18 Dec 2023 Bing Wang, Changyu Ren, Jian Yang, Xinnian Liang, Jiaqi Bai, Linzheng Chai, Zhao Yan, Qian-Wen Zhang, Di Yin, Xing Sun, Zhoujun Li

Our framework comprises a core decomposer agent for Text-to-SQL generation with few-shot chain-of-thought reasoning, accompanied by two auxiliary agents that utilize external tools or models to acquire smaller sub-databases and refine erroneous SQL queries.

SQL Parsing Text-To-SQL

FAGC:Feature Augmentation on Geodesic Curve in the Pre-Shape Space

no code implementations6 Dec 2023 Yuexing Han, Guanxin Wan, Bing Wang

Finally, the many generated features on the Geodesic curve are used to train the various machine learning models.

Data Augmentation

Backbone-based Dynamic Graph Spatio-Temporal Network for Epidemic Forecasting

no code implementations1 Dec 2023 Junkai Mao, Yuexing Han, Gouhei Tanaka, Bing Wang

To capture this property, we use adaptive methods to generate static backbone graphs containing the primary information and temporal models to generate dynamic temporal graphs of epidemic data, fusing them to generate a backbone-based dynamic graph.

Early detection of inflammatory arthritis to improve referrals using multimodal machine learning from blood testing, semi-structured and unstructured patient records

no code implementations30 Oct 2023 Bing Wang, Weizi Li, Anthony Bradlow, Antoni T. Y. Chan, Eghosa Bazuaye

But in practice, blood testing data is not always available at the point of referrals, so we need methods to leverage multimodal data such as semi-structured and unstructured data for early detection of IA.

Conformal Prediction Decision Making +1

Improving Opioid Use Disorder Risk Modelling through Behavioral and Genetic Feature Integration

1 code implementation19 Sep 2023 Sybille Légitime, Kaustubh Prabhu, Devin McConnell, Bing Wang, Dipak K. Dey, Derek Aguiar

Opioids are an effective analgesic for acute and chronic pain, but also carry a considerable risk of addiction leading to millions of opioid use disorder (OUD) cases and tens of thousands of premature deaths in the United States yearly.

Decision Making Experimental Design

RenderOcc: Vision-Centric 3D Occupancy Prediction with 2D Rendering Supervision

1 code implementation18 Sep 2023 Mingjie Pan, Jiaming Liu, Renrui Zhang, Peixiang Huang, Xiaoqi Li, Bing Wang, Hongwei Xie, Li Liu, Shanghang Zhang

3D occupancy prediction holds significant promise in the fields of robot perception and autonomous driving, which quantifies 3D scenes into grid cells with semantic labels.

Autonomous Driving

Drone-NeRF: Efficient NeRF Based 3D Scene Reconstruction for Large-Scale Drone Survey

no code implementations30 Aug 2023 Zhihao Jia, Bing Wang, Changhao Chen

In this work, we propose the Drone-NeRF framework to enhance the efficient reconstruction of unbounded large-scale scenes suited for drone oblique photography using Neural Radiance Fields (NeRF).

3D Scene Reconstruction Neural Rendering

Deep Learning for Visual Localization and Mapping: A Survey

no code implementations27 Aug 2023 Changhao Chen, Bing Wang, Chris Xiaoxuan Lu, Niki Trigoni, Andrew Markham

Deep learning based localization and mapping approaches have recently emerged as a new research direction and receive significant attentions from both industry and academia.

Simultaneous Localization and Mapping Visual Localization +1

MPSTAN: Metapopulation-based Spatio-Temporal Attention Network for Epidemic Forecasting

no code implementations15 Jun 2023 Junkai Mao, Yuexing Han, Bing Wang

Most of the present spatio-temporal models cannot provide a general framework for stable, and accurate forecasting of epidemics with diverse evolution trends.

GrowSP: Unsupervised Semantic Segmentation of 3D Point Clouds

1 code implementation CVPR 2023 Zihui Zhang, Bo Yang, Bing Wang, Bo Li

Our method consists of three major components, 1) the feature extractor to learn per-point features from input point clouds, 2) the superpoint constructor to progressively grow the sizes of superpoints, and 3) the semantic primitive clustering module to group superpoints into semantic elements for the final semantic segmentation.

3D Semantic Segmentation Segmentation +1

Non-stationary Projection-free Online Learning with Dynamic and Adaptive Regret Guarantees

no code implementations19 May 2023 Yibo Wang, Wenhao Yang, Wei Jiang, Shiyin Lu, Bing Wang, Haihong Tang, Yuanyu Wan, Lijun Zhang

Specifically, we first provide a novel dynamic regret analysis for an existing projection-free method named $\text{BOGD}_\text{IP}$, and establish an $\mathcal{O}(T^{3/4}(1+P_T))$ dynamic regret bound, where $P_T$ denotes the path-length of the comparator sequence.

Unsupervised Sentence Representation Learning with Frequency-induced Adversarial Tuning and Incomplete Sentence Filtering

1 code implementation15 May 2023 Bing Wang, Ximing Li, Zhiyao Yang, Yuanyuan Guan, Jiayin Li, Shengsheng Wang

To solve the problems, we fine-tune PLMs by leveraging the frequency information of words and propose a novel USRL framework, namely Sentence Representation Learning with Frequency-induced Adversarial tuning and Incomplete sentence filtering (SLT-FAI).

Language Modelling Sentence +1

Enhancing Large Language Model with Self-Controlled Memory Framework

1 code implementation26 Apr 2023 Bing Wang, Xinnian Liang, Jian Yang, Hui Huang, Shuangzhi Wu, Peihao Wu, Lu Lu, Zejun Ma, Zhoujun Li

Large Language Models (LLMs) are constrained by their inability to process lengthy inputs, resulting in the loss of critical historical information.

Book summarization Document Summarization +5

DAA: A Delta Age AdaIN operation for age estimation via binary code transformer

1 code implementation CVPR 2023 Ping Chen, Xingpeng Zhang, Ye Li, Ju Tao, Bin Xiao, Bing Wang, Zongjie Jiang

Inspired by the transfer learning, we designed the Delta Age AdaIN (DAA) operation to obtain the feature difference with each age, which obtains the style map of each age through the learned values representing the mean and standard deviation.

Age Estimation Transfer Learning

Decoupling Skill Learning from Robotic Control for Generalizable Object Manipulation

no code implementations7 Mar 2023 Kai Lu, Bo Yang, Bing Wang, Andrew Markham

Our experiments on manipulating complex articulated objects show that the proposed approach is more generalizable to unseen objects with large intra-class variations, outperforming previous approaches.

Imitation Learning Reinforcement Learning (RL)

Towards Robustness of Text-to-SQL Models Against Natural and Realistic Adversarial Table Perturbation

1 code implementation ACL 2022 Xinyu Pi, Bing Wang, Yan Gao, Jiaqi Guo, Zhoujun Li, Jian-Guang Lou

The robustness of Text-to-SQL parsers against adversarial perturbations plays a crucial role in delivering highly reliable applications.


Know What I don't Know: Handling Ambiguous and Unanswerable Questions for Text-to-SQL

1 code implementation17 Dec 2022 Bing Wang, Yan Gao, Zhoujun Li, Jian-Guang Lou

Following this study, we propose a simple yet effective counterfactual example generation approach that automatically produces ambiguous and unanswerable text-to-SQL examples.

counterfactual Text-To-SQL

DM-NeRF: 3D Scene Geometry Decomposition and Manipulation from 2D Images

1 code implementation15 Aug 2022 Bing Wang, Lu Chen, Bo Yang

In this paper, we study the problem of 3D scene geometry decomposition and manipulation from 2D views.


Learning an Adaptive Forwarding Strategy for Mobile Wireless Networks: Resource Usage vs. Latency

no code implementations23 Jul 2022 Victoria Manfredi, Alicia P. Wolfe, Xiaolan Zhang, Bing Wang

Designing effective routing strategies for mobile wireless networks is challenging due to the need to seamlessly adapt routing behavior to spatially diverse and temporally changing network conditions.

RangeUDF: Semantic Surface Reconstruction from 3D Point Clouds

2 code implementations19 Apr 2022 Bing Wang, Zhengdi Yu, Bo Yang, Jie Qin, Toby Breckon, Ling Shao, Niki Trigoni, Andrew Markham

We present RangeUDF, a new implicit representation based framework to recover the geometry and semantics of continuous 3D scene surfaces from point clouds.

Semantic Segmentation Surface Reconstruction

A Contrastive Cross-Channel Data Augmentation Framework for Aspect-based Sentiment Analysis

1 code implementation COLING 2022 Bing Wang, Liang Ding, Qihuang Zhong, Ximing Li, DaCheng Tao

Aspect-based sentiment analysis (ABSA) is a fine-grained sentiment analysis task, which focuses on detecting the sentiment polarity towards the aspect in a sentence.

Aspect-Based Sentiment Analysis Aspect-Based Sentiment Analysis (ABSA) +4

Exploring Inter-Channel Correlation for Diversity-preserved KnowledgeDistillation

1 code implementation8 Feb 2022 Li Liu, Qingle Huang, Sihao Lin, Hongwei Xie, Bing Wang, Xiaojun Chang, Xiaodan Liang

Extensive experiments on two vision tasks, includ-ing ImageNet classification and Pascal VOC segmentation, demonstrate the superiority of our ICKD, which consis-tently outperforms many existing methods, advancing thestate-of-the-art in the fields of Knowledge Distillation.

Diversity Knowledge Distillation

Contrastive Instruction-Trajectory Learning for Vision-Language Navigation

1 code implementation8 Dec 2021 Xiwen Liang, Fengda Zhu, Yi Zhu, Bingqian Lin, Bing Wang, Xiaodan Liang

The vision-language navigation (VLN) task requires an agent to reach a target with the guidance of natural language instruction.

Contrastive Learning Navigate +1

Weakly Supervised Prototype Topic Model with Discriminative Seed Words: Modifying the Category Prior by Self-exploring Supervised Signals

no code implementations20 Nov 2021 Bing Wang, Yue Wang, Ximing Li, Jihong Ouyang

The recent generative dataless methods construct document-specific category priors by using seed word occurrences only, however, such category priors often contain very limited and even noisy supervised signals.

text-classification Text Classification +1

CubeLearn: End-to-end Learning for Human Motion Recognition from Raw mmWave Radar Signals

1 code implementation7 Nov 2021 Peijun Zhao, Chris Xiaoxuan Lu, Bing Wang, Niki Trigoni, Andrew Markham

To avoid the drawbacks of conventional DFT pre-processing, we propose a learnable pre-processing module, named CubeLearn, to directly extract features from raw radar signal and build an end-to-end deep neural network for mmWave FMCW radar motion recognition applications.

Activity Recognition

A novel class of fixed-time consensus protocols for multi-agent systems with simple dynamics

no code implementations30 Sep 2021 Yuquan Chen, Fumian Wang, Bing Wang

This paper investigates the fixed-time consensus problem for a class of multi-agent systems with simple dynamics.

Iterative Memory Network for Long Sequential User Behavior Modeling in Recommender Systems

no code implementations29 Sep 2021 Qianying Lin, Wen-Ji Zhou, Yanshi Wang, Qing Da, Qing-Guo Chen, Bing Wang

Extensive empirical studies show that our method outperforms various state-of-the-art sequential modeling methods on both public and industrial datasets for long sequential user behavior modeling.

Recommendation Systems

An AI-assisted Economic Model of Endogenous Mobility and Infectious Diseases: The Case of COVID-19 in the United States

no code implementations21 Sep 2021 Lin William Cong, Ke Tang, Bing Wang, Jingyuan Wang

We build a deep-learning-based SEIR-AIM model integrating the classical Susceptible-Exposed-Infectious-Removed epidemiology model with forecast modules of infection, community mobility, and unemployment.


DS-Net++: Dynamic Weight Slicing for Efficient Inference in CNNs and Transformers

1 code implementation21 Sep 2021 Changlin Li, Guangrun Wang, Bing Wang, Xiaodan Liang, Zhihui Li, Xiaojun Chang

Dynamic networks have shown their promising capability in reducing theoretical computation complexity by adapting their architectures to the input during inference.

Fairness Model Compression

Dynamic Slimmable Network

1 code implementation CVPR 2021 Changlin Li, Guangrun Wang, Bing Wang, Xiaodan Liang, Zhihui Li, Xiaojun Chang

Here, we explore a dynamic network slimming regime, named Dynamic Slimmable Network (DS-Net), which aims to achieve good hardware-efficiency via dynamically adjusting filter numbers of networks at test time with respect to different inputs, while keeping filters stored statically and contiguously in hardware to prevent the extra burden.

Fairness Model Compression

BossNAS: Exploring Hybrid CNN-transformers with Block-wisely Self-supervised Neural Architecture Search

1 code implementation ICCV 2021 Changlin Li, Tao Tang, Guangrun Wang, Jiefeng Peng, Bing Wang, Xiaodan Liang, Xiaojun Chang

In this work, we present Block-wisely Self-supervised Neural Architecture Search (BossNAS), an unsupervised NAS method that addresses the problem of inaccurate architecture rating caused by large weight-sharing space and biased supervision in previous methods.

Image Classification Neural Architecture Search +1

Exploring Inter-Channel Correlation for Diversity-Preserved Knowledge Distillation

2 code implementations ICCV 2021 Li Liu, Qingle Huang, Sihao Lin, Hongwei Xie, Bing Wang, Xiaojun Chang, Xiaodan Liang

Extensive experiments on two vision tasks, including ImageNet classification and Pascal VOC segmentation, demonstrate the superiority of our ICKD, which consistently outperforms many existing methods, advancing the state-of-the-art in the fields of Knowledge Distillation.

Diversity Knowledge Distillation

Relational Deep Reinforcement Learning for Routing in Wireless Networks

no code implementations31 Dec 2020 Victoria Manfredi, Alicia Wolfe, Bing Wang, Xiaolan Zhang

While routing in wireless networks has been studied extensively, existing protocols are typically designed for a specific set of network conditions and so cannot accommodate any drastic changes in those conditions.

reinforcement-learning Reinforcement Learning (RL)

Photonic Floquet time crystals

no code implementations15 Dec 2020 Bing Wang, Jiaqi Quan, Jianfei Han, Xiaopeng Shen, Hongwei Wu, Yiming Pan

The public and scientists constantly have different perspectives.

Quantum Physics Mesoscale and Nanoscale Physics Other Condensed Matter Optics

PSF-LO: Parameterized Semantic Features Based Lidar Odometry

no code implementations26 Oct 2020 Guibin Chen, BoSheng Wang, Xiaoliang Wang, Huanjun Deng, Bing Wang, Shuo Zhang

Lidar odometry (LO) is a key technology in numerous reliable and accurate localization and mapping systems of autonomous driving.

Autonomous Driving Motion Estimation +1

VMLoc: Variational Fusion For Learning-Based Multimodal Camera Localization

1 code implementation12 Mar 2020 Kaichen Zhou, Changhao Chen, Bing Wang, Muhamad Risqi U. Saputra, Niki Trigoni, Andrew Markham

We conjecture that this is because of the naive approaches to feature space fusion through summation or concatenation which do not take into account the different strengths of each modality.

Camera Relocalization Visual Localization

PointLoc: Deep Pose Regressor for LiDAR Point Cloud Localization

2 code implementations5 Mar 2020 Wei Wang, Bing Wang, Peijun Zhao, Changhao Chen, Ronald Clark, Bo Yang, Andrew Markham, Niki Trigoni

In this paper, we present a novel end-to-end learning-based LiDAR relocalization framework, termed PointLoc, which infers 6-DoF poses directly using only a single point cloud as input, without requiring a pre-built map.


Learning Selective Sensor Fusion for States Estimation

no code implementations30 Dec 2019 Changhao Chen, Stefano Rosa, Chris Xiaoxuan Lu, Bing Wang, Niki Trigoni, Andrew Markham

By integrating the observations from different sensors, these mobile agents are able to perceive the environment and estimate system states, e. g. locations and orientations.

Autonomous Vehicles Sensor Fusion

Chinese Spelling Error Detection Using a Fusion Lattice LSTM

no code implementations25 Nov 2019 Hao Wang, Bing Wang, Jianyong Duan, Jiajun Zhang

Spelling error detection serves as a crucial preprocessing in many natural language processing applications.

See Through Smoke: Robust Indoor Mapping with Low-cost mmWave Radar

1 code implementation1 Nov 2019 Chris Xiaoxuan Lu, Stefano Rosa, Peijun Zhao, Bing Wang, Changhao Chen, John A. Stankovic, Niki Trigoni, Andrew Markham

This paper presents the design, implementation and evaluation of milliMap, a single-chip millimetre wave (mmWave) radar based indoor mapping system targetted towards low-visibility environments to assist in emergency response.

AtLoc: Attention Guided Camera Localization

1 code implementation8 Sep 2019 Bing Wang, Changhao Chen, Chris Xiaoxuan Lu, Peijun Zhao, Niki Trigoni, Andrew Markham

Deep learning has achieved impressive results in camera localization, but current single-image techniques typically suffer from a lack of robustness, leading to large outliers.

Camera Localization Visual Localization

DynaNet: Neural Kalman Dynamical Model for Motion Estimation and Prediction

no code implementations11 Aug 2019 Changhao Chen, Chris Xiaoxuan Lu, Bing Wang, Niki Trigoni, Andrew Markham

In addition we show how DynaNet can indicate failures through investigation of properties such as the rate of innovation (Kalman Gain).

Motion Estimation Sensor Fusion +1

X-LineNet: Detecting Aircraft in Remote Sensing Images by a pair of Intersecting Line Segments

no code implementations29 Jul 2019 Hao-Ran Wei, Yue Zhang, Bing Wang, Yang Yang, Hao Li, Hongqi Wang

Motivated by the development of deep convolution neural networks (DCNNs), tremendous progress has been gained in the field of aircraft detection.

Accelerating Primal Solution Findings for Mixed Integer Programs Based on Solution Prediction

no code implementations23 Jun 2019 Jian-Ya Ding, Chao Zhang, Lei Shen, Shengyin Li, Bing Wang, Yinghui Xu, Le Song

In many applications, a similar MIP model is solved on a regular basis, maintaining remarkable similarities in model structures and solution appearances but differing in formulation coefficients.

Combinatorial Optimization

Learning Hierarchical Features for Visual Object Tracking with Recursive Neural Networks

no code implementations6 Jan 2018 Li Wang, Ting Liu, Bing Wang, Xulei Yang, Gang Wang

First, we learn RNN parameters to discriminate between the target object and background in the first frame of a test sequence.

Object Visual Object Tracking

Joint Calibration of Panoramic Camera and Lidar Based on Supervised Learning

no code implementations9 Sep 2017 Mingwei Cao, Ming Yang, Chunxiang Wang, Yeqiang Qian, Bing Wang

In view of contemporary panoramic camera-laser scanner system, the traditional calibration method is not suitable for panoramic cameras whose imaging model is extremely nonlinear.


Joint Learning of Siamese CNNs and Temporally Constrained Metrics for Tracklet Association

no code implementations15 May 2016 Bing Wang, Li Wang, Bing Shuai, Zhen Zuo, Ting Liu, Kap Luk Chan, Gang Wang

Then the Siamese CNN and temporally constrained metrics are jointly learned online to construct the appearance-based tracklet affinity models.

Multi-Object Tracking Multi-Task Learning

Tracklet Association by Online Target-Specific Metric Learning and Coherent Dynamics Estimation

no code implementations20 Nov 2015 Bing Wang, Gang Wang, Kap Luk Chan, Li Wang

In this paper, we present a novel method based on online target-specific metric learning and coherent dynamics estimation for tracklet (track fragment) association by network flow optimization in long-term multi-person tracking.

Metric Learning Object

Learning Contextual Dependencies with Convolutional Hierarchical Recurrent Neural Networks

no code implementations13 Sep 2015 Zhen Zuo, Bing Shuai, Gang Wang, Xiao Liu, Xingxing Wang, Bing Wang

In this manuscript, we integrate CNNs with HRNNs, and develop end-to-end convolutional hierarchical recurrent neural networks (C-HRNNs).

General Classification Image Classification

DAG-Recurrent Neural Networks For Scene Labeling

no code implementations CVPR 2016 Bing Shuai, Zhen Zuo, Gang Wang, Bing Wang

In image labeling, local representations for image units are usually generated from their surrounding image patches, thus long-range contextual information is not effectively encoded.

General Classification Scene Labeling +1

Integrating Parametric and Non-Parametric Models For Scene Labeling

no code implementations CVPR 2015 Bing Shuai, Gang Wang, Zhen Zuo, Bing Wang, Lifan Zhao

We adopt Convolutional Neural Networks (CNN) as our parametric model to learn discriminative features and classifiers for local patch classification.

General Classification Metric Learning +1

Tracklet Association with Online Target-Specific Metric Learning

no code implementations CVPR 2014 Bing Wang, Gang Wang, Kap Luk Chan, Li Wang

In our method, target-specific similarity metrics are learned, which give rise to the appearance-based models used in the tracklet affinity estimation.

Metric Learning

Radial basis function process neural network training based on generalized frechet distance and GA-SA hybrid strategy

no code implementations9 Jan 2014 Bing Wang, Yao-hua Meng, Xiao-hong Yu

For learning problem of Radial Basis Function Process Neural Network (RBF-PNN), an optimization training method based on GA combined with SA is proposed in this paper.

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