Search Results for author: Ming Zhu

Found 27 papers, 9 papers with code

Why Not Transform Chat Large Language Models to Non-English?

1 code implementation22 May 2024 Xiang Geng, Ming Zhu, Jiahuan Li, Zhejian Lai, Wei Zou, Shuaijie She, Jiaxin Guo, Xiaofeng Zhao, Yinglu Li, Yuang Li, Chang Su, Yanqing Zhao, Xinglin Lyu, Min Zhang, Jiajun Chen, Hao Yang, ShuJian Huang

For the second issue, we propose a method comprising two synergistic components: low-rank adaptation for training to maintain the original LLM parameters, and recovery KD, which utilizes data generated by the chat LLM itself to recover the original knowledge from the frozen parameters.

Knowledge Distillation

InfiAgent-DABench: Evaluating Agents on Data Analysis Tasks

1 code implementation10 Jan 2024 Xueyu Hu, Ziyu Zhao, Shuang Wei, Ziwei Chai, Qianli Ma, Guoyin Wang, Xuwu Wang, Jing Su, Jingjing Xu, Ming Zhu, Yao Cheng, Jianbo Yuan, Jiwei Li, Kun Kuang, Yang Yang, Hongxia Yang, Fei Wu

In this paper, we introduce InfiAgent-DABench, the first benchmark specifically designed to evaluate LLM-based agents on data analysis tasks.


Mental Health Diagnosis in the Digital Age: Harnessing Sentiment Analysis on Social Media Platforms upon Ultra-Sparse Feature Content

no code implementations9 Nov 2023 Haijian Shao, Ming Zhu, Shengjie Zhai

To address these issues, we propose a novel semantic feature preprocessing technique with a three-folded structure: 1) mitigating the feature sparsity with a weak classifier, 2) adaptive feature dimension with modulus loops, and 3) deep-mining and extending features among the contexts.

Multi-Label Classification Navigate +1

Dynamic Datasets and Market Environments for Financial Reinforcement Learning

4 code implementations25 Apr 2023 Xiao-Yang Liu, Ziyi Xia, Hongyang Yang, Jiechao Gao, Daochen Zha, Ming Zhu, Christina Dan Wang, Zhaoran Wang, Jian Guo

The financial market is a particularly challenging playground for deep reinforcement learning due to its unique feature of dynamic datasets.


Deep Reinforcement Learning for Traffic Light Control in Intelligent Transportation Systems

no code implementations4 Feb 2023 Xiao-Yang Liu, Ming Zhu, Sem Borst, Anwar Walid

In this paper, we investigate deep reinforcement learning to control traffic lights, and both theoretical analysis and numerical experiments show that the intelligent behavior ``greenwave" (i. e., a vehicle will see a progressive cascade of green lights, and not have to brake at any intersection) emerges naturally a grid road network, which is proved to be the optimal policy in an avenue with multiple cross streets.

reinforcement-learning Reinforcement Learning (RL)

FinRL-Meta: Market Environments and Benchmarks for Data-Driven Financial Reinforcement Learning

4 code implementations6 Nov 2022 Xiao-Yang Liu, Ziyi Xia, Jingyang Rui, Jiechao Gao, Hongyang Yang, Ming Zhu, Christina Dan Wang, Zhaoran Wang, Jian Guo

However, establishing high-quality market environments and benchmarks for financial reinforcement learning is challenging due to three major factors, namely, low signal-to-noise ratio of financial data, survivorship bias of historical data, and model overfitting in the backtesting stage.

reinforcement-learning Reinforcement Learning (RL)

XLCoST: A Benchmark Dataset for Cross-lingual Code Intelligence

1 code implementation16 Jun 2022 Ming Zhu, Aneesh Jain, Karthik Suresh, Roshan Ravindran, Sindhu Tipirneni, Chandan K. Reddy

To the best of our knowledge, it is the largest parallel dataset for source code both in terms of size and the number of languages.

Code Search

StructCoder: Structure-Aware Transformer for Code Generation

1 code implementation10 Jun 2022 Sindhu Tipirneni, Ming Zhu, Chandan K. Reddy

This paper addresses the problem of code generation, where the goal is to generate target code given source code in a different language or a natural language description.

Code Translation Decoder +1

PointAugmenting: Cross-Modal Augmentation for 3D Object Detection

no code implementations CVPR 2021 Chunwei Wang, Chao Ma, Ming Zhu, Xiaokang Yang

On one hand, PointAugmenting decorates point clouds with corresponding point-wise CNN features extracted by pretrained 2D detection models, and then performs 3D object detection over the decorated point clouds.

3D Object Detection Autonomous Driving +4

A Dataset And Benchmark Of Underwater Object Detection For Robot Picking

no code implementations10 Jun 2021 Chongwei Liu, Haojie Li, Shuchang Wang, Ming Zhu, Dong Wang, Xin Fan, Zhihui Wang

Towards these challenges we introduce a dataset, Detecting Underwater Objects (DUO), and a corresponding benchmark, based on the collection and re-annotation of all relevant datasets.

object-detection Object Detection

Extragalactic HI 21-cm absorption line observations with the Five-hundred-meter Aperture Spherical radio Telescope

no code implementations11 Mar 2021 Bo Zhang, Ming Zhu, Zhong-Zu Wu, Qing-Zheng Yu, Peng Jiang, You-Ling Yue, Meng-Lin Huang, Qiao-Li Hao

Our observations successfully confirmed the existence of HI absorption lines in all these systems, including two sources that were marginally detected by ALFALFA.

Astrophysics of Galaxies

Convolutional Graph-Tensor Net for Graph Data Completion

no code implementations7 Mar 2021 Xiao-Yang Liu, Ming Zhu

Graph data completion is a fundamentally important issue as data generally has a graph structure, e. g., social networks, recommendation systems, and the Internet of Things.

Recommendation Systems

Question Answering with Long Multiple-Span Answers

1 code implementation Findings of the Association for Computational Linguistics 2020 Ming Zhu, Aman Ahuja, Da-Cheng Juan, Wei Wei, Chandan K. Reddy

To this end, we present MASH-QA, a Multiple Answer Spans Healthcare Question Answering dataset from the consumer health domain, where answers may need to be excerpted from multiple, non-consecutive parts of text spanned across a long document.

Question Answering Sentence

Cross-Modality 3D Object Detection

no code implementations16 Aug 2020 Ming Zhu, Chao Ma, Pan Ji, Xiaokang Yang

In this paper, we focus on exploring the fusion of images and point clouds for 3D object detection in view of the complementary nature of the two modalities, i. e., images possess more semantic information while point clouds specialize in distance sensing.

3D Classification 3D Object Detection +4

LATTE: Latent Type Modeling for Biomedical Entity Linking

no code implementations21 Nov 2019 Ming Zhu, Busra Celikkaya, Parminder Bhatia, Chandan K. Reddy

This is of significant importance in the biomedical domain, where it could be used to semantically annotate a large volume of clinical records and biomedical literature, to standardized concepts described in an ontology such as Unified Medical Language System (UMLS).

Entity Disambiguation Entity Linking +1

Low-light Image Enhancement Algorithm Based on Retinex and Generative Adversarial Network

no code implementations14 Jun 2019 Yangming Shi, Xiaopo Wu, Ming Zhu

In this work, the authors propose a novel approach for processing low-light images based on the Retinex theory and generative adversarial network (GAN), which is composed of the decomposition part for splitting the image into illumination image and reflected image, and the enhancement part for generating high-quality image.

Generative Adversarial Network Low-Light Image Enhancement

Deep Reinforcement Learning for Unmanned Aerial Vehicle-Assisted Vehicular Networks

no code implementations12 Jun 2019 Ming Zhu, Xiao-Yang Liu, Xiaodong Wang

Unmanned aerial vehicles (UAVs) are envisioned to complement the 5G communication infrastructure in future smart cities.

reinforcement-learning Reinforcement Learning (RL)

Real-world Underwater Enhancement: Challenges, Benchmarks, and Solutions

1 code implementation15 Jan 2019 Risheng Liu, Xin Fan, Ming Zhu, Minjun Hou, Zhongxuan Luo

Underwater image enhancement is such an important low-level vision task with many applications that numerous algorithms have been proposed in recent years.

Image Enhancement object-detection +1

Background Subtraction with Real-time Semantic Segmentation

no code implementations25 Nov 2018 Dongdong Zeng, Xiang Chen, Ming Zhu, Michael Goesele, Arjan Kuijper

Our proposed framework consists of two components, a traditional BGS segmenter $\mathcal{B}$ and a real-time semantic segmenter $\mathcal{S}$.

Foreground Segmentation Object Tracking +1

A Robust Local Binary Similarity Pattern for Foreground Object Detection

no code implementations16 Oct 2018 Dongdong Zeng, Ming Zhu, Hang Yang

First, we propose a robust texture operator named Robust Local Binary Similarity Pattern (RLBSP), which shows strong robustness to illumination variations and dynamic backgrounds.

Object object-detection +2

Combining Background Subtraction Algorithms with Convolutional Neural Network

no code implementations5 Jul 2018 Dongdong Zeng, Ming Zhu, Arjan Kuijper

Accurate and fast extraction of foreground object is a key prerequisite for a wide range of computer vision applications such as object tracking and recognition.

Decoder Object +3

An Online Ride-Sharing Path Planning Strategy for Public Vehicle Systems

no code implementations27 Dec 2017 Ming Zhu, Xiao-Yang Liu, Xiaodong Wang

As efficient traffic-management platforms, public vehicle (PV) systems are envisioned to be a promising approach to solving traffic congestions and pollutions for future smart cities.

Management Scheduling

Guided Filter based Edge-preserving Image Non-blind Deconvolution

no code implementations7 Sep 2016 Hang Yang, Ming Zhu, Zhongbo Zhang, He-Yan Huang

In the denoising step, the guided filter is used with the two obtained images for efficient edge-preserving filtering.

Deblurring Denoising +1

Dual Domain Filters Based Texture and Structure Preserving Image Non-Blind Deconvolution

no code implementations CVPR 2015 Hang Yang, Ming Zhu, Yan Niu, Yujing Guan, Zhongbo Zhang

Image deconvolution continues to be an active research topic of recovering a sharp image, given a blurry one generated by a convolution.

Deblurring Image Deconvolution

Contractive De-noising Auto-encoder

no code implementations17 May 2013 Fu-qiang Chen, Yan Wu, Guo-dong Zhao, Jun-ming Zhang, Ming Zhu, Jing Bai

Auto-encoder is a special kind of neural network based on reconstruction.

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