Search Results for author: Liang Zhao

Found 241 papers, 89 papers with code

The ManDi Corpus: A Spoken Corpus of Mandarin Regional Dialects

no code implementations LREC 2022 Liang Zhao, Eleanor Chodroff

In the present paper, we introduce the ManDi Corpus, a spoken corpus of regional Mandarin dialects and Standard Mandarin.

PerPO: Perceptual Preference Optimization via Discriminative Rewarding

no code implementations5 Feb 2025 Zining Zhu, Liang Zhao, Kangheng Lin, Jinze Yang, En Yu, Chenglong Liu, Haoran Wei, Jianjian Sun, Zheng Ge, Xiangyu Zhang

This paper presents Perceptual Preference Optimization (PerPO), a perception alignment method aimed at addressing the visual discrimination challenges in generative pre-trained multimodal large language models (MLLMs).

Machine Learning-Driven Student Performance Prediction for Enhancing Tiered Instruction

no code implementations5 Feb 2025 Yawen Chen, Jiande Sun, Jinhui Wang, Liang Zhao, Xinmin Song, Linbo Zhai

To this end, this study integrates the results of machine learning-based student performance prediction with tiered instruction, aiming to enhance student outcomes in target course, which is significant for the application of educational data mining in contemporary teaching scenarios.

feature selection Prediction

PolyhedronNet: Representation Learning for Polyhedra with Surface-attributed Graph

1 code implementation3 Feb 2025 Dazhou Yu, Genpei Zhang, Liang Zhao

This study proposes \textbf{PolyhedronNet}, a general framework tailored for learning representations of 3D polyhedral objects.

Representation Learning

CG-RAG: Research Question Answering by Citation Graph Retrieval-Augmented LLMs

no code implementations25 Jan 2025 Yuntong Hu, Zhihan Lei, Zhongjie Dai, Allen Zhang, Abhinav Angirekula, Zheng Zhang, Liang Zhao

In this paper, we introduce Contextualized Graph Retrieval-Augmented Generation (CG-RAG), a novel framework that integrates sparse and dense retrieval signals within graph structures to enhance retrieval efficiency and subsequently improve generation quality for research question answering.

Information Retrieval Question Answering +2

DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

2 code implementations22 Jan 2025 DeepSeek-AI, Daya Guo, Dejian Yang, Haowei Zhang, Junxiao Song, Ruoyu Zhang, Runxin Xu, Qihao Zhu, Shirong Ma, Peiyi Wang, Xiao Bi, Xiaokang Zhang, Xingkai Yu, Yu Wu, Z. F. Wu, Zhibin Gou, Zhihong Shao, Zhuoshu Li, Ziyi Gao, Aixin Liu, Bing Xue, Bingxuan Wang, Bochao Wu, Bei Feng, Chengda Lu, Chenggang Zhao, Chengqi Deng, Chenyu Zhang, Chong Ruan, Damai Dai, Deli Chen, Dongjie Ji, Erhang Li, Fangyun Lin, Fucong Dai, Fuli Luo, Guangbo Hao, Guanting Chen, Guowei Li, H. Zhang, Han Bao, Hanwei Xu, Haocheng Wang, Honghui Ding, Huajian Xin, Huazuo Gao, Hui Qu, Hui Li, JianZhong Guo, Jiashi Li, Jiawei Wang, Jingchang Chen, Jingyang Yuan, Junjie Qiu, Junlong Li, J. L. Cai, Jiaqi Ni, Jian Liang, Jin Chen, Kai Dong, Kai Hu, Kaige Gao, Kang Guan, Kexin Huang, Kuai Yu, Lean Wang, Lecong Zhang, Liang Zhao, Litong Wang, Liyue Zhang, Lei Xu, Leyi Xia, Mingchuan Zhang, Minghua Zhang, Minghui Tang, Meng Li, Miaojun Wang, Mingming Li, Ning Tian, Panpan Huang, Peng Zhang, Qiancheng Wang, Qinyu Chen, Qiushi Du, Ruiqi Ge, Ruisong Zhang, Ruizhe Pan, Runji Wang, R. J. Chen, R. L. Jin, Ruyi Chen, Shanghao Lu, Shangyan Zhou, Shanhuang Chen, Shiyu Wang, Shuiping Yu, Shunfeng Zhou, Shuting Pan, S. S. Li, Shuang Zhou, Shaoqing Wu, Shengfeng Ye, Tao Yun, Tian Pei, Tianyu Sun, T. Wang, Wangding Zeng, Wanjia Zhao, Wen Liu, Wenfeng Liang, Wenjun Gao, Wenqin Yu, Wentao Zhang, W. L. Xiao, Wei An, Xiaodong Liu, Xiaohan Wang, Xiaokang Chen, Xiaotao Nie, Xin Cheng, Xin Liu, Xin Xie, Xingchao Liu, Xinyu Yang, Xinyuan Li, Xuecheng Su, Xuheng Lin, X. Q. Li, Xiangyue Jin, Xiaojin Shen, Xiaosha Chen, Xiaowen Sun, Xiaoxiang Wang, Xinnan Song, Xinyi Zhou, Xianzu Wang, Xinxia Shan, Y. K. Li, Y. Q. Wang, Y. X. Wei, Yang Zhang, Yao Li, Yao Zhao, Yaofeng Sun, Yaohui Wang, Yi Yu, Yichao Zhang, Yifan Shi, Yiliang Xiong, Ying He, Yishi Piao, Yisong Wang, Yixuan Tan, Yiyang Ma, Yiyuan Liu, Yongqiang Guo, Yuan Ou, Yuduan Wang, Yue Gong, Yuheng Zou, Yujia He, Yunfan Xiong, Yuxiang Luo, Yuxiang You, Yuxuan Liu, Yuyang Zhou, Y. X. Zhu, Yanhong Xu, Yanping Huang, Yaohui Li, Yi Zheng, Yuchen Zhu, Yunxian Ma, Ying Tang, Yukun Zha, Yuting Yan, Z. Z. Ren, Zehui Ren, Zhangli Sha, Zhe Fu, Zhean Xu, Zhenda Xie, Zhengyan Zhang, Zhewen Hao, Zhicheng Ma, Zhigang Yan, Zhiyu Wu, Zihui Gu, Zijia Zhu, Zijun Liu, Zilin Li, Ziwei Xie, Ziyang Song, Zizheng Pan, Zhen Huang, Zhipeng Xu, Zhongyu Zhang, Zhen Zhang

We introduce our first-generation reasoning models, DeepSeek-R1-Zero and DeepSeek-R1.

Mathematical Reasoning Reinforcement Learning (RL)

The Robustness of Spiking Neural Networks in Federated Learning with Compression Against Non-omniscient Byzantine Attacks

no code implementations6 Jan 2025 Manh V. Nguyen, Liang Zhao, Bobin Deng, Shaoen Wu

Spiking Neural Networks (SNNs), which offer exceptional energy efficiency for inference, and Federated Learning (FL), which offers privacy-preserving distributed training, is a rising area of interest that highly beneficial towards Internet of Things (IoT) devices.

Federated Learning Privacy Preserving

Slow Perception: Let's Perceive Geometric Figures Step-by-step

no code implementations30 Dec 2024 Haoran Wei, Youyang Yin, Yumeng Li, Jia Wang, Liang Zhao, Jianjian Sun, Zheng Ge, Xiangyu Zhang, Daxin Jiang

Recently, "visual o1" began to enter people's vision, with expectations that this slow-thinking design can solve visual reasoning tasks, especially geometric math problems.

Math Visual Reasoning

DeepSeek-V3 Technical Report

1 code implementation27 Dec 2024 DeepSeek-AI, Aixin Liu, Bei Feng, Bing Xue, Bingxuan Wang, Bochao Wu, Chengda Lu, Chenggang Zhao, Chengqi Deng, Chenyu Zhang, Chong Ruan, Damai Dai, Daya Guo, Dejian Yang, Deli Chen, Dongjie Ji, Erhang Li, Fangyun Lin, Fucong Dai, Fuli Luo, Guangbo Hao, Guanting Chen, Guowei Li, H. Zhang, Han Bao, Hanwei Xu, Haocheng Wang, Haowei Zhang, Honghui Ding, Huajian Xin, Huazuo Gao, Hui Li, Hui Qu, J. L. Cai, Jian Liang, JianZhong Guo, Jiaqi Ni, Jiashi Li, Jiawei Wang, Jin Chen, Jingchang Chen, Jingyang Yuan, Junjie Qiu, Junlong Li, Junxiao Song, Kai Dong, Kai Hu, Kaige Gao, Kang Guan, Kexin Huang, Kuai Yu, Lean Wang, Lecong Zhang, Lei Xu, Leyi Xia, Liang Zhao, Litong Wang, Liyue Zhang, Meng Li, Miaojun Wang, Mingchuan Zhang, Minghua Zhang, Minghui Tang, Mingming Li, Ning Tian, Panpan Huang, Peiyi Wang, Peng Zhang, Qiancheng Wang, Qihao Zhu, Qinyu Chen, Qiushi Du, R. J. Chen, R. L. Jin, Ruiqi Ge, Ruisong Zhang, Ruizhe Pan, Runji Wang, Runxin Xu, Ruoyu Zhang, Ruyi Chen, S. S. Li, Shanghao Lu, Shangyan Zhou, Shanhuang Chen, Shaoqing Wu, Shengfeng Ye, Shirong Ma, Shiyu Wang, Shuang Zhou, Shuiping Yu, Shunfeng Zhou, Shuting Pan, T. Wang, Tao Yun, Tian Pei, Tianyu Sun, W. L. Xiao, Wangding Zeng, Wanjia Zhao, Wei An, Wen Liu, Wenfeng Liang, Wenjun Gao, Wenqin Yu, Wentao Zhang, X. Q. Li, Xiangyue Jin, Xianzu Wang, Xiao Bi, Xiaodong Liu, Xiaohan Wang, Xiaojin Shen, Xiaokang Chen, Xiaokang Zhang, Xiaosha Chen, Xiaotao Nie, Xiaowen Sun, Xiaoxiang Wang, Xin Cheng, Xin Liu, Xin Xie, Xingchao Liu, Xingkai Yu, Xinnan Song, Xinxia Shan, Xinyi Zhou, Xinyu Yang, Xinyuan Li, Xuecheng Su, Xuheng Lin, Y. K. Li, Y. Q. Wang, Y. X. Wei, Y. X. Zhu, Yang Zhang, Yanhong Xu, Yanping Huang, Yao Li, Yao Zhao, Yaofeng Sun, Yaohui Li, Yaohui Wang, Yi Yu, Yi Zheng, Yichao Zhang, Yifan Shi, Yiliang Xiong, Ying He, Ying Tang, Yishi Piao, Yisong Wang, Yixuan Tan, Yiyang Ma, Yiyuan Liu, Yongqiang Guo, Yu Wu, Yuan Ou, Yuchen Zhu, Yuduan Wang, Yue Gong, Yuheng Zou, Yujia He, Yukun Zha, Yunfan Xiong, Yunxian Ma, Yuting Yan, Yuxiang Luo, Yuxiang You, Yuxuan Liu, Yuyang Zhou, Z. F. Wu, Z. Z. Ren, Zehui Ren, Zhangli Sha, Zhe Fu, Zhean Xu, Zhen Huang, Zhen Zhang, Zhenda Xie, Zhengyan Zhang, Zhewen Hao, Zhibin Gou, Zhicheng Ma, Zhigang Yan, Zhihong Shao, Zhipeng Xu, Zhiyu Wu, Zhongyu Zhang, Zhuoshu Li, Zihui Gu, Zijia Zhu, Zijun Liu, Zilin Li, Ziwei Xie, Ziyang Song, Ziyi Gao, Zizheng Pan

We present DeepSeek-V3, a strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token.

Language Modeling Language Modelling

Cognition Chain for Explainable Psychological Stress Detection on Social Media

no code implementations18 Dec 2024 Xin Wang, Boyan Gao, Yi Dai, Lei Cao, Liang Zhao, Yibo Yang, David Clifton

We further study the benefits brought by the proposed Cognition Chain format by utilising it as a synthetic dataset generation template for LLMs instruction-tuning and introduce CogInstruct, an instruction-tuning dataset for stress detection.

Dataset Generation

TSGaussian: Semantic and Depth-Guided Target-Specific Gaussian Splatting from Sparse Views

1 code implementation13 Dec 2024 Liang Zhao, Zehan Bao, Yi Xie, Hong Chen, Yaohui Chen, Weifu Li

Recent advances in Gaussian Splatting have significantly advanced the field, achieving both panoptic and interactive segmentation of 3D scenes.

Interactive Segmentation Novel View Synthesis

Activation Sparsity Opportunities for Compressing General Large Language Models

no code implementations13 Dec 2024 Nobel Dhar, Bobin Deng, Md Romyull Islam, Kazi Fahim Ahmad Nasif, Liang Zhao, Kun Suo

To obtain the benefits of activation sparsity, we provide a guideline for the system architect for LLM prediction and prefetching.

Model Compression

Implicit Neural Compression of Point Clouds

no code implementations11 Dec 2024 Hongning Ruan, Yulin Shao, Qianqian Yang, Liang Zhao, Zhaoyang Zhang, Dusit Niyato

Our approach employs two coordinate-based neural networks to implicitly represent a voxelized point cloud: the first determines the occupancy status of a voxel, while the second predicts the attributes of occupied voxels.

Attribute

MEGL: Multimodal Explanation-Guided Learning

no code implementations20 Nov 2024 Yifei Zhang, Tianxu Jiang, Bo Pan, Jingyu Wang, Guangji Bai, Liang Zhao

A Visual Explanation Distribution Consistency loss further reinforces visual coherence by aligning the generated visual explanations with dataset-level patterns, enabling the model to effectively learn from incomplete multimodal supervision.

Image Classification

CLIC: Contrastive Learning Framework for Unsupervised Image Complexity Representation

1 code implementation19 Nov 2024 Shipeng Liu, Liang Zhao, Dengfeng Chen

As an essential visual attribute, image complexity affects human image comprehension and directly influences the performance of computer vision tasks.

Attribute Contrastive Learning +1

JanusFlow: Harmonizing Autoregression and Rectified Flow for Unified Multimodal Understanding and Generation

1 code implementation12 Nov 2024 Yiyang Ma, Xingchao Liu, Xiaokang Chen, Wen Liu, Chengyue Wu, Zhiyu Wu, Zizheng Pan, Zhenda Xie, Haowei Zhang, Xingkai Yu, Liang Zhao, Yisong Wang, Jiaying Liu, Chong Ruan

To further improve the performance of our unified model, we adopt two key strategies: (i) decoupling the understanding and generation encoders, and (ii) aligning their representations during unified training.

Language Modeling Language Modelling +2

YOLO-Vehicle-Pro: A Cloud-Edge Collaborative Framework for Object Detection in Autonomous Driving under Adverse Weather Conditions

no code implementations23 Oct 2024 Xiguang Li, Jiafu Chen, Yunhe Sun, Na Lin, Ammar Hawbani, Liang Zhao

With the rapid advancement of autonomous driving technology, efficient and accurate object detection capabilities have become crucial factors in ensuring the safety and reliability of autonomous driving systems.

Autonomous Driving Image Dehazing +3

TAGExplainer: Narrating Graph Explanations for Text-Attributed Graph Learning Models

no code implementations20 Oct 2024 Bo Pan, Zhen Xiong, Guanchen Wu, Zheng Zhang, Yifei Zhang, Liang Zhao

Despite advancements in TAG learning methodologies, challenges remain in explainability due to the black-box nature of existing TAG representation learning models.

Decision Making Graph Learning +6

FedSpaLLM: Federated Pruning of Large Language Models

no code implementations18 Oct 2024 Guangji Bai, Yijiang Li, Zilinghan Li, Liang Zhao, Kibaek Kim

Large Language Models (LLMs) achieve state-of-the-art performance but are challenging to deploy due to their high computational and storage demands.

Federated Learning Privacy Preserving

Advancing Large Language Model Attribution through Self-Improving

no code implementations17 Oct 2024 Lei Huang, Xiaocheng Feng, Weitao Ma, Liang Zhao, Yuchun Fan, Weihong Zhong, Dongliang Xu, Qing Yang, Hongtao Liu, Bing Qin

Teaching large language models (LLMs) to generate text with citations to evidence sources can mitigate hallucinations and enhance verifiability in information-seeking systems.

Language Modeling Language Modelling +2

HiReview: Hierarchical Taxonomy-Driven Automatic Literature Review Generation

no code implementations2 Oct 2024 Yuntong Hu, Zhuofeng Li, Zheng Zhang, Chen Ling, Raasikh Kanjiani, Boxin Zhao, Liang Zhao

In this work, we present HiReview, a novel framework for hierarchical taxonomy-driven automatic literature review generation.

Clustering Review Generation

The Robustness of Spiking Neural Networks in Communication and its Application towards Network Efficiency in Federated Learning

no code implementations19 Sep 2024 Manh V. Nguyen, Liang Zhao, Bobin Deng, William Severa, Honghui Xu, Shaoen Wu

Spiking Neural Networks (SNNs) have recently gained significant interest in on-chip learning in embedded devices and emerged as an energy-efficient alternative to conventional Artificial Neural Networks (ANNs).

Federated Learning

Few-Shot Class-Incremental Learning with Non-IID Decentralized Data

no code implementations18 Sep 2024 Cuiwei Liu, Siang Xu, Huaijun Qiu, Jing Zhang, Zhi Liu, Liang Zhao

Within this framework, a noise-aware generative replay module is developed to fine-tune local models with a balance of new and replay data, while generating synthetic data of new classes to further expand the replay buffer for future tasks.

class-incremental learning Few-Shot Class-Incremental Learning +3

LibMOON: A Gradient-based MultiObjective OptimizatioN Library in PyTorch

1 code implementation4 Sep 2024 Xiaoyuan Zhang, Liang Zhao, Yingying Yu, Xi Lin, Yifan Chen, Han Zhao, Qingfu Zhang

Multiobjective optimization problems (MOPs) are prevalent in machine learning, with applications in multi-task learning, learning under fairness or robustness constraints, etc.

Evolutionary Algorithms Fairness +2

4D-CAT: Synthesis of 4D Coronary Artery Trees from Systole and Diastole

no code implementations3 Sep 2024 Daosong Hu, Ruomeng Wang, Liang Zhao, Mingyue Cui, Song Ding, Kai Huang

In this paper, we propose a method for generating a 4D coronary artery trees, which maps the systole to the diastole through deformation field prediction, interpolates on the timeline, and the motion trajectory of points are obtained.

Medical Diagnosis

Representation Learning of Geometric Trees

no code implementations16 Aug 2024 Zheng Zhang, Allen Zhang, Ruth Nelson, Giorgio Ascoli, Liang Zhao

Geometric trees are characterized by their tree-structured layout and spatially constrained nodes and edges, which significantly impacts their topological attributes.

Representation Learning Self-Supervised Learning

Cycle-Configuration: A Novel Graph-theoretic Descriptor Set for Molecular Inference

1 code implementation9 Aug 2024 Bowen Song, Jianshen Zhu, Naveed Ahmed Azam, Kazuya Haraguchi, Liang Zhao, Tatsuya Akutsu

In this paper, we propose a novel family of descriptors of chemical graphs, named cycle-configuration (CC), that can be used in the standard "two-layered (2L) model" of mol-infer, a molecular inference framework based on mixed integer linear programming (MILP) and machine learning (ML).

Contrastive Learning for Image Complexity Representation

no code implementations6 Aug 2024 Shipeng Liu, Liang Zhao, Dengfeng Chen, Zhanping Song

The results demonstrate that the performance of CLIC is comparable to that of state-of-the-art supervised methods.

Contrastive Learning Diversity

CLII: Visual-Text Inpainting via Cross-Modal Predictive Interaction

no code implementations23 Jul 2024 Liang Zhao, Qing Guo, Xiaoguang Li, Song Wang

In this work, we identify the visual-text inpainting task to achieve high-quality scene text image restoration and text completion: Given a scene text image with unknown missing regions and the corresponding text with unknown missing characters, we aim to complete the missing information in both images and text by leveraging their complementary information.

Image Inpainting Image Restoration +1

Skywork-Math: Data Scaling Laws for Mathematical Reasoning in Large Language Models -- The Story Goes On

no code implementations11 Jul 2024 Liang Zeng, Liangjun Zhong, Liang Zhao, Tianwen Wei, Liu Yang, Jujie He, Cheng Cheng, Rui Hu, Yang Liu, Shuicheng Yan, Han Fang, Yahui Zhou

In this paper, we investigate the underlying factors that potentially enhance the mathematical reasoning capabilities of large language models (LLMs).

GSM8K Math +1

PolygonGNN: Representation Learning for Polygonal Geometries with Heterogeneous Visibility Graph

1 code implementation30 Jun 2024 Dazhou Yu, Yuntong Hu, Yun Li, Liang Zhao

Finally, we introduce Multipolygon-GNN, a novel model tailored to leverage the spatial and semantic heterogeneity inherent in the visibility graph.

Computational Efficiency Geographic Question Answering +2

Investigating and Mitigating the Multimodal Hallucination Snowballing in Large Vision-Language Models

1 code implementation30 Jun 2024 Weihong Zhong, Xiaocheng Feng, Liang Zhao, Qiming Li, Lei Huang, Yuxuan Gu, Weitao Ma, Yuan Xu, Bing Qin

To mitigate this, we further propose a training-free method called Residual Visual Decoding, where we revise the output distribution of LVLMs with the one derived from the residual visual input, providing models with direct access to the visual information.

Hallucination multimodal interaction

Self-consistent Deep Geometric Learning for Heterogeneous Multi-source Spatial Point Data Prediction

1 code implementation30 Jun 2024 Dazhou Yu, Xiaoyun Gong, Yun Li, Meikang Qiu, Liang Zhao

Existing models in this area often fall short due to their domain-specific nature and lack a strategy for integrating information from various sources in the absence of ground truth labels.

Graph Neural Network

LatentExplainer: Explaining Latent Representations in Deep Generative Models with Multimodal Large Language Models

1 code implementation21 Jun 2024 Mengdan Zhu, Raasikh Kanjiani, Jiahui Lu, Andrew Choi, Qirui Ye, Liang Zhao

Deep generative models like VAEs and diffusion models have advanced various generation tasks by leveraging latent variables to learn data distributions and generate high-quality samples.

Uncertainty Quantification

A transformer boosted UNet for smoke segmentation in complex backgrounds in multispectral LandSat imagery

no code implementations18 Jun 2024 Jixue Liu, Jiuyong Li, Stefan Peters, Liang Zhao

To show the advantages of the proposed model, the paper presents extensive results for various possible model architectures improving UNet and draws interesting conclusions including that adding more modules to a model does not always lead to a better performance.

Incorporating uncertainty quantification into travel mode choice modeling: a Bayesian neural network (BNN) approach and an uncertainty-guided active survey framework

no code implementations16 Jun 2024 Shuwen Zheng, Zhou Fang, Liang Zhao

With BTMP, we further propose an uncertainty-guided active survey framework, which dynamically formulates survey questions representing travel mode choice scenarios with high prediction uncertainty.

Explainable artificial intelligence Prediction +2

TEG-DB: A Comprehensive Dataset and Benchmark of Textual-Edge Graphs

1 code implementation14 Jun 2024 Zhuofeng Li, Zixing Gou, Xiangnan Zhang, Zhongyuan Liu, Sirui Li, Yuntong Hu, Chen Ling, Zheng Zhang, Liang Zhao

To address this gap, we introduce Textual-Edge Graphs Datasets and Benchmark (TEG-DB), a comprehensive and diverse collection of benchmark textual-edge datasets featuring rich textual descriptions on nodes and edges.

TAG

Skywork-MoE: A Deep Dive into Training Techniques for Mixture-of-Experts Language Models

1 code implementation3 Jun 2024 Tianwen Wei, Bo Zhu, Liang Zhao, Cheng Cheng, Biye Li, Weiwei Lü, Peng Cheng, Jianhao Zhang, XiaoYu Zhang, Liang Zeng, Xiaokun Wang, Yutuan Ma, Rui Hu, Shuicheng Yan, Han Fang, Yahui Zhou

In this technical report, we introduce the training methodologies implemented in the development of Skywork-MoE, a high-performance mixture-of-experts (MoE) large language model (LLM) with 146 billion parameters and 16 experts.

Language Modeling Language Modelling +1

TAGA: Text-Attributed Graph Self-Supervised Learning by Synergizing Graph and Text Mutual Transformations

no code implementations27 May 2024 Zheng Zhang, Yuntong Hu, Bo Pan, Chen Ling, Liang Zhao

Text-Attributed Graphs (TAGs) enhance graph structures with natural language descriptions, enabling detailed representation of data and their relationships across a broad spectrum of real-world scenarios.

Representation Learning Self-Supervised Learning +1

Network Interdiction Goes Neural

no code implementations26 May 2024 Lei Zhang, Zhiqian Chen, Chang-Tien Lu, Liang Zhao

Network interdiction problems are combinatorial optimization problems involving two players: one aims to solve an optimization problem on a network, while the other seeks to modify the network to thwart the first player's objectives.

Combinatorial Optimization Graph Matching +1

GRAG: Graph Retrieval-Augmented Generation

no code implementations26 May 2024 Yuntong Hu, Zhihan Lei, Zheng Zhang, Bo Pan, Chen Ling, Liang Zhao

Naive Retrieval-Augmented Generation (RAG) focuses on individual documents during retrieval and, as a result, falls short in handling networked documents which are very popular in many applications such as citation graphs, social media, and knowledge graphs.

Entity Retrieval Knowledge Graphs +2

Deep Causal Generative Models with Property Control

no code implementations25 May 2024 Qilong Zhao, Shiyu Wang, Guangji Bai, Bo Pan, Zhaohui Qin, Liang Zhao

This is due to the long-lasting challenge of jointly identifying key latent variables, their causal relations, and their correlation with properties of interest, as well as how to leverage their discoveries toward causally controlled data generation.

Continuous Temporal Domain Generalization

1 code implementation25 May 2024 Zekun Cai, Guangji Bai, Renhe Jiang, Xuan Song, Liang Zhao

Temporal Domain Generalization (TDG) addresses the challenge of training predictive models under temporally varying data distributions.

Domain Generalization

Focus Anywhere for Fine-grained Multi-page Document Understanding

1 code implementation23 May 2024 Chenglong Liu, Haoran Wei, Jinyue Chen, Lingyu Kong, Zheng Ge, Zining Zhu, Liang Zhao, Jianjian Sun, Chunrui Han, Xiangyu Zhang

Modern LVLMs still struggle to achieve fine-grained document understanding, such as OCR/translation/caption for regions of interest to the user, tasks that require the context of the entire page, or even multiple pages.

document understanding Optical Character Recognition (OCR)

Point Cloud Compression with Implicit Neural Representations: A Unified Framework

no code implementations19 May 2024 Hongning Ruan, Yulin Shao, Qianqian Yang, Liang Zhao, Dusit Niyato

By feeding the coordinates of these voxels into the respective networks, we reconstruct the geometry and attribute components of the original point cloud.

Attribute

DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model

4 code implementations7 May 2024 DeepSeek-AI, Aixin Liu, Bei Feng, Bin Wang, Bingxuan Wang, Bo Liu, Chenggang Zhao, Chengqi Dengr, Chong Ruan, Damai Dai, Daya Guo, Dejian Yang, Deli Chen, Dongjie Ji, Erhang Li, Fangyun Lin, Fuli Luo, Guangbo Hao, Guanting Chen, Guowei Li, H. Zhang, Hanwei Xu, Hao Yang, Haowei Zhang, Honghui Ding, Huajian Xin, Huazuo Gao, Hui Li, Hui Qu, J. L. Cai, Jian Liang, JianZhong Guo, Jiaqi Ni, Jiashi Li, Jin Chen, Jingyang Yuan, Junjie Qiu, Junxiao Song, Kai Dong, Kaige Gao, Kang Guan, Lean Wang, Lecong Zhang, Lei Xu, Leyi Xia, Liang Zhao, Liyue Zhang, Meng Li, Miaojun Wang, Mingchuan Zhang, Minghua Zhang, Minghui Tang, Mingming Li, Ning Tian, Panpan Huang, Peiyi Wang, Peng Zhang, Qihao Zhu, Qinyu Chen, Qiushi Du, R. J. Chen, R. L. Jin, Ruiqi Ge, Ruizhe Pan, Runxin Xu, Ruyi Chen, S. S. Li, Shanghao Lu, Shangyan Zhou, Shanhuang Chen, Shaoqing Wu, Shengfeng Ye, Shirong Ma, Shiyu Wang, Shuang Zhou, Shuiping Yu, Shunfeng Zhou, Size Zheng, T. Wang, Tian Pei, Tian Yuan, Tianyu Sun, W. L. Xiao, Wangding Zeng, Wei An, Wen Liu, Wenfeng Liang, Wenjun Gao, Wentao Zhang, X. Q. Li, Xiangyue Jin, Xianzu Wang, Xiao Bi, Xiaodong Liu, Xiaohan Wang, Xiaojin Shen, Xiaokang Chen, Xiaosha Chen, Xiaotao Nie, Xiaowen Sun, Xiaoxiang Wang, Xin Liu, Xin Xie, Xingkai Yu, Xinnan Song, Xinyi Zhou, Xinyu Yang, Xuan Lu, Xuecheng Su, Y. Wu, Y. K. Li, Y. X. Wei, Y. X. Zhu, Yanhong Xu, Yanping Huang, Yao Li, Yao Zhao, Yaofeng Sun, Yaohui Li, Yaohui Wang, Yi Zheng, Yichao Zhang, Yiliang Xiong, Yilong Zhao, Ying He, Ying Tang, Yishi Piao, Yixin Dong, Yixuan Tan, Yiyuan Liu, Yongji Wang, Yongqiang Guo, Yuchen Zhu, Yuduan Wang, Yuheng Zou, Yukun Zha, Yunxian Ma, Yuting Yan, Yuxiang You, Yuxuan Liu, Z. Z. Ren, Zehui Ren, Zhangli Sha, Zhe Fu, Zhen Huang, Zhen Zhang, Zhenda Xie, Zhewen Hao, Zhihong Shao, Zhiniu Wen, Zhipeng Xu, Zhongyu Zhang, Zhuoshu Li, Zihan Wang, Zihui Gu, Zilin Li, Ziwei Xie

MLA guarantees efficient inference through significantly compressing the Key-Value (KV) cache into a latent vector, while DeepSeekMoE enables training strong models at an economical cost through sparse computation.

Language Modeling Language Modelling +1

GraphSL: An Open-Source Library for Graph Source Localization Approaches and Benchmark Datasets

1 code implementation6 May 2024 Junxiang Wang, Liang Zhao

We introduce GraphSL, a new library for studying the graph source localization problem.

Self-Supervised Visual Preference Alignment

1 code implementation16 Apr 2024 Ke Zhu, Zheng Ge, Liang Zhao, Xiangyu Zhang

We generate chosen and rejected responses with regard to the original and augmented image pairs, and conduct preference alignment with direct preference optimization.

8k MM-Vet +1

OneChart: Purify the Chart Structural Extraction via One Auxiliary Token

1 code implementation15 Apr 2024 Jinyue Chen, Lingyu Kong, Haoran Wei, Chenglong Liu, Zheng Ge, Liang Zhao, Jianjian Sun, Chunrui Han, Xiangyu Zhang

To address this, we propose OneChart: a reliable agent specifically devised for the structural extraction of chart information.

Decoder

DUE: Dynamic Uncertainty-Aware Explanation Supervision via 3D Imputation

no code implementations16 Mar 2024 Qilong Zhao, Yifei Zhang, Mengdan Zhu, Siyi Gu, Yuyang Gao, Xiaofeng Yang, Liang Zhao

Explanation supervision aims to enhance deep learning models by integrating additional signals to guide the generation of model explanations, showcasing notable improvements in both the predictability and explainability of the model.

Imputation

SparseLLM: Towards Global Pruning for Pre-trained Language Models

2 code implementations28 Feb 2024 Guangji Bai, Yijiang Li, Chen Ling, Kibaek Kim, Liang Zhao

The transformative impact of large language models (LLMs) like LLaMA and GPT on natural language processing is countered by their prohibitive computational demands.

Computational Efficiency Problem Decomposition

MIM-Reasoner: Learning with Theoretical Guarantees for Multiplex Influence Maximization

1 code implementation24 Feb 2024 Nguyen Do, Tanmoy Chowdhury, Chen Ling, Liang Zhao, My T. Thai

Multiplex influence maximization (MIM) asks us to identify a set of seed users such as to maximize the expected number of influenced users in a multiplex network.

ELAD: Explanation-Guided Large Language Models Active Distillation

no code implementations20 Feb 2024 Yifei Zhang, Bo Pan, Chen Ling, Yuntong Hu, Liang Zhao

The deployment and application of Large Language Models (LLMs) is hindered by their memory inefficiency, computational demands, and the high costs of API inferences.

Active Learning Knowledge Distillation

Distilling Large Language Models for Text-Attributed Graph Learning

no code implementations19 Feb 2024 Bo Pan, Zheng Zhang, Yifei Zhang, Yuntong Hu, Liang Zhao

To address the inherent gaps between LLMs (generative models for texts) and graph models (discriminative models for graphs), we propose first to let LLMs teach an interpreter with rich textual rationale and then let a student model mimic the interpreter's reasoning without LLMs' textual rationale.

Graph Learning TAG

A Condensed Transition Graph Framework for Zero-shot Link Prediction with Large Language Models

no code implementations16 Feb 2024 Mingchen Li, Chen Ling, Rui Zhang, Liang Zhao

To address this, in this work, we introduce a Condensed Transition Graph Framework for Zero-Shot Link Prediction (CTLP), which encodes all the paths' information in linear time complexity to predict unseen relations between entities, attaining both efficiency and information preservation.

Contrastive Learning Knowledge Graphs +1

Uncertainty Quantification for In-Context Learning of Large Language Models

1 code implementation15 Feb 2024 Chen Ling, Xujiang Zhao, Xuchao Zhang, Wei Cheng, Yanchi Liu, Yiyou Sun, Mika Oishi, Takao Osaki, Katsushi Matsuda, Jie Ji, Guangji Bai, Liang Zhao, Haifeng Chen

Existing works have been devoted to quantifying the uncertainty in LLM's response, but they often overlook the complex nature of LLMs and the uniqueness of in-context learning.

Hallucination In-Context Learning +1

NK Hybrid Genetic Algorithm for Clustering

1 code implementation6 Feb 2024 Renato Tinós, Liang Zhao, Francisco Chicano, Darrell Whitley

Mutation operators, a partition crossover, and a local search strategy are proposed, all using information about the relationship between decision variables.

Clustering

Explaining latent representations of generative models with large multimodal models

no code implementations2 Feb 2024 Mengdan Zhu, Zhenke Liu, Bo Pan, Abhinav Angirekula, Liang Zhao

Learning interpretable representations of data generative latent factors is an important topic for the development of artificial intelligence.

Disentanglement Explanation Generation

3DPFIX: Improving Remote Novices' 3D Printing Troubleshooting through Human-AI Collaboration

no code implementations29 Jan 2024 Nahyun Kwon, Tong Sun, Yuyang Gao, Liang Zhao, Xu Wang, Jeeeun Kim, Sungsoo Ray Hong

While troubleshooting plays an essential part of 3D printing, the process remains challenging for many remote novices even with the help of well-developed online sources, such as online troubleshooting archives and online community help.

Small Language Model Meets with Reinforced Vision Vocabulary

no code implementations23 Jan 2024 Haoran Wei, Lingyu Kong, Jinyue Chen, Liang Zhao, Zheng Ge, En Yu, Jianjian Sun, Chunrui Han, Xiangyu Zhang

In Vary-toy, we introduce an improved vision vocabulary, allowing the model to not only possess all features of Vary but also gather more generality.

Language Modeling Language Modelling +4

Gene-associated Disease Discovery Powered by Large Language Models

no code implementations16 Jan 2024 Jiayu Chang, Shiyu Wang, Chen Ling, Zhaohui Qin, Liang Zhao

The intricate relationship between genetic variation and human diseases has been a focal point of medical research, evidenced by the identification of risk genes regarding specific diseases.

Decision Making Retrieval

Beyond Efficiency: A Systematic Survey of Resource-Efficient Large Language Models

1 code implementation1 Jan 2024 Guangji Bai, Zheng Chai, Chen Ling, Shiyu Wang, Jiaying Lu, Nan Zhang, Tingwei Shi, Ziyang Yu, Mengdan Zhu, Yifei Zhang, Xinyuan Song, Carl Yang, Yue Cheng, Liang Zhao

We categorize methods based on their optimization focus: computational, memory, energy, financial, and network resources and their applicability across various stages of an LLM's lifecycle, including architecture design, pretraining, finetuning, and system design.

Survey

POND: Multi-Source Time Series Domain Adaptation with Information-Aware Prompt Tuning

no code implementations19 Dec 2023 Junxiang Wang, Guangji Bai, Wei Cheng, Zhengzhang Chen, Liang Zhao, Haifeng Chen

In order to tackle these challenges simultaneously, in this paper, we introduce PrOmpt-based domaiN Discrimination (POND), the first framework to utilize prompts for time series domain adaptation.

Domain Adaptation Fault Diagnosis +4

Non-Euclidean Spatial Graph Neural Network

1 code implementation17 Dec 2023 Zheng Zhang, Sirui Li, Jingcheng Zhou, Junxiang Wang, Abhinav Angirekula, Allen Zhang, Liang Zhao

Besides, existing spatial network representation learning methods can only consider networks embedded in Euclidean space, and can not well exploit the rich geometric information carried by irregular and non-uniform non-Euclidean space.

Graph Neural Network Representation Learning

Merlin:Empowering Multimodal LLMs with Foresight Minds

no code implementations30 Nov 2023 En Yu, Liang Zhao, Yana Wei, Jinrong Yang, Dongming Wu, Lingyu Kong, Haoran Wei, Tiancai Wang, Zheng Ge, Xiangyu Zhang, Wenbing Tao

Then, FIT requires MLLMs to first predict trajectories of related objects and then reason about potential future events based on them.

Visual Question Answering

SkyMath: Technical Report

1 code implementation25 Oct 2023 Liu Yang, Haihua Yang, Wenjun Cheng, Lei Lin, Chenxia Li, Yifu Chen, Lunan Liu, Jianfei Pan, Tianwen Wei, Biye Li, Liang Zhao, Lijie Wang, Bo Zhu, Guoliang Li, Xuejie Wu, Xilin Luo, Rui Hu

Large language models (LLMs) have shown great potential to solve varieties of natural language processing (NLP) tasks, including mathematical reasoning.

GSM8K Language Modeling +3

Open-ended Commonsense Reasoning with Unrestricted Answer Scope

no code implementations18 Oct 2023 Chen Ling, Xuchao Zhang, Xujiang Zhao, Yanchi Liu, Wei Cheng, Mika Oishi, Takao Osaki, Katsushi Matsuda, Haifeng Chen, Liang Zhao

In this work, we leverage pre-trained language models to iteratively retrieve reasoning paths on the external knowledge base, which does not require task-specific supervision.

Question Answering Retrieval

Exploring Damping Effect of Inner Control Loops for Grid-Forming VSCs

no code implementations14 Oct 2023 Liang Zhao, Xiongfei Wang, Zheming Jin

This paper presents an analytical approach to explore the damping effect of inner loops on grid-forming converters.

Visual Attention Prompted Prediction and Learning

1 code implementation12 Oct 2023 Yifei Zhang, Siyi Gu, Bo Pan, Guangji Bai, Meikang Qiu, Xiaofeng Yang, Liang Zhao

However, in many real-world situations, it is usually desired to prompt the model with visual attention without model retraining.

Cancer Classification Decision Making +1

XAI Benchmark for Visual Explanation

no code implementations12 Oct 2023 Yifei Zhang, Siyi Gu, James Song, Bo Pan, Guangji Bai, Liang Zhao

Our proposed benchmarks facilitate a fair evaluation and comparison of visual explanation methods.

Decision Making Explainable artificial intelligence +2

SurroCBM: Concept Bottleneck Surrogate Models for Generative Post-hoc Explanation

no code implementations11 Oct 2023 Bo Pan, Zhenke Liu, Yifei Zhang, Liang Zhao

Explainable AI seeks to bring light to the decision-making processes of black-box models.

Decision Making

Controllable Data Generation Via Iterative Data-Property Mutual Mappings

no code implementations11 Oct 2023 Bo Pan, Muran Qin, Shiyu Wang, Yifei Zhang, Liang Zhao

To address these challenges, in this paper, we propose a general framework to enhance VAE-based data generators with property controllability and ensure disentanglement.

Disentanglement

Balancing Specialized and General Skills in LLMs: The Impact of Modern Tuning and Data Strategy

no code implementations7 Oct 2023 Zheng Zhang, Chen Zheng, Da Tang, Ke Sun, Yukun Ma, Yingtong Bu, Xun Zhou, Liang Zhao

This paper introduces a multifaceted methodology for fine-tuning and evaluating large language models (LLMs) for specialized monetization tasks.

Transferable Deep Clustering Model

no code implementations7 Oct 2023 Zheng Zhang, Liang Zhao

Deep learning has shown remarkable success in the field of clustering recently.

Clustering Deep Clustering +2

Large Language Models for Spatial Trajectory Patterns Mining

no code implementations7 Oct 2023 Zheng Zhang, Hossein Amiri, Zhenke Liu, Andreas Züfle, Liang Zhao

Identifying anomalous human spatial trajectory patterns can indicate dynamic changes in mobility behavior with applications in domains like infectious disease monitoring and elderly care.

Anomaly Detection

Beyond Text: A Deep Dive into Large Language Models' Ability on Understanding Graph Data

no code implementations7 Oct 2023 Yuntong Hu, Zheng Zhang, Liang Zhao

Large language models (LLMs) have achieved impressive performance on many natural language processing tasks.

Benchmarking

Saliency-Guided Hidden Associative Replay for Continual Learning

1 code implementation6 Oct 2023 Guangji Bai, Qilong Zhao, Xiaoyang Jiang, Yifei Zhang, Liang Zhao

Continual Learning is a burgeoning domain in next-generation AI, focusing on training neural networks over a sequence of tasks akin to human learning.

Continual Learning Retrieval

Multi-Prompt Fine-Tuning of Foundation Models for Enhanced Medical Image Segmentation

no code implementations3 Oct 2023 Xiangru Li, Yifei Zhang, Liang Zhao

The Segment Anything Model (SAM) is a powerful foundation model that introduced revolutionary advancements in natural image segmentation.

Decoder Image Segmentation +3

DreamLLM: Synergistic Multimodal Comprehension and Creation

1 code implementation20 Sep 2023 Runpei Dong, Chunrui Han, Yuang Peng, Zekun Qi, Zheng Ge, Jinrong Yang, Liang Zhao, Jianjian Sun, HongYu Zhou, Haoran Wei, Xiangwen Kong, Xiangyu Zhang, Kaisheng Ma, Li Yi

This paper presents DreamLLM, a learning framework that first achieves versatile Multimodal Large Language Models (MLLMs) empowered with frequently overlooked synergy between multimodal comprehension and creation.

multimodal generation Visual Question Answering +2

Helper Recommendation with seniority control in Online Health Community

no code implementations6 Sep 2023 Junruo Gao, Chen Ling, Carl Yang, Liang Zhao

Online health communities (OHCs) are forums where patients with similar conditions communicate their experiences and provide moral support.

Recommendation Systems

Feature Attention Network (FA-Net): A Deep-Learning Based Approach for Underwater Single Image Enhancement

no code implementations30 Aug 2023 Muhammad Hamza, Ammar Hawbani, Sami Ul Rehman, Xingfu Wang, Liang Zhao

In particular, we propose a Residual Feature Attention Block (RFAB), containing the channel attention, pixel attention, and residual learning mechanism with long and short skip connections.

Image Enhancement

Staleness-Alleviated Distributed GNN Training via Online Dynamic-Embedding Prediction

no code implementations25 Aug 2023 Guangji Bai, Ziyang Yu, Zheng Chai, Yue Cheng, Liang Zhao

It utilizes an offline memory to cache historical information (e. g., node embedding) as an affordable approximation of the exact value and achieves high concurrency.

Distributed Computing

ChatSpot: Bootstrapping Multimodal LLMs via Precise Referring Instruction Tuning

no code implementations18 Jul 2023 Liang Zhao, En Yu, Zheng Ge, Jinrong Yang, Haoran Wei, HongYu Zhou, Jianjian Sun, Yuang Peng, Runpei Dong, Chunrui Han, Xiangyu Zhang

Based on precise referring instruction, we propose ChatSpot, a unified end-to-end multimodal large language model that supports diverse forms of interactivity including mouse clicks, drag-and-drop, and drawing boxes, which provides a more flexible and seamless interactive experience.

Instruction Following Language Modeling +3

Designing a Direct Feedback Loop between Humans and Convolutional Neural Networks through Local Explanations

1 code implementation8 Jul 2023 Tong Steven Sun, Yuyang Gao, Shubham Khaladkar, Sijia Liu, Liang Zhao, Young-Ho Kim, Sungsoo Ray Hong

To mitigate the gap, we designed DeepFuse, the first interactive design that realizes the direct feedback loop between a user and CNNs in diagnosing and revising CNN's vulnerability using local explanations.

Explainable Artificial Intelligence (XAI)

Leveraging GPT-4 for Food Effect Summarization to Enhance Product-Specific Guidance Development via Iterative Prompting

no code implementations28 Jun 2023 Yiwen Shi, Ping Ren, Jing Wang, Biao Han, Taha ValizadehAslani, Felix Agbavor, Yi Zhang, Meng Hu, Liang Zhao, Hualou Liang

Specifically, we propose a three-turn iterative prompting approach to food effect summarization in which the keyword-focused and length-controlled prompts are respectively provided in consecutive turns to refine the quality of the generated summary.

Text Summarization

A Review on Knowledge Graphs for Healthcare: Resources, Applications, and Promises

no code implementations7 Jun 2023 Hejie Cui, Jiaying Lu, ran Xu, Shiyu Wang, Wenjing Ma, Yue Yu, Shaojun Yu, Xuan Kan, Chen Ling, Liang Zhao, Zhaohui S. Qin, Joyce C. Ho, Tianfan Fu, Jing Ma, Mengdi Huai, Fei Wang, Carl Yang

This comprehensive review aims to provide an overview of the current state of Healthcare Knowledge Graphs (HKGs), including their construction, utilization models, and applications across various healthcare and biomedical research domains.

Knowledge Graphs

JGAT: a joint spatio-temporal graph attention model for brain decoding

1 code implementation3 Jun 2023 Han Yi Chiu, Liang Zhao, Anqi Wu

However, traditional approaches for integrating FC and SC overlook the dynamical variations, which stand a great chance to over-generalize the brain neural network.

Brain Decoding Functional Connectivity +1

Graph Neural Network for spatiotemporal data: methods and applications

no code implementations30 May 2023 Yun Li, Dazhou Yu, Zhenke Liu, Minxing Zhang, Xiaoyun Gong, Liang Zhao

Graph neural networks (GNNs) have emerged as a powerful tool for modeling and understanding data with dependencies to each other such as spatial and temporal dependencies.

Graph Neural Network Weather Forecasting

Domain Generalization Deep Graph Transformation

no code implementations19 May 2023 Shiyu Wang, Guangji Bai, Qingyang Zhu, Zhaohui Qin, Liang Zhao

As a result, domain generalization graph transformation that predicts graphs not available in the training data is under-explored, with multiple key challenges to be addressed including (1) the extreme space complexity when training on all input-output mode combinations, (2) difference of graph topologies between the input and the output modes, and (3) how to generalize the model to (unseen) target domains that are not in the training data.

Decoder Domain Generalization +2

Deep Graph Representation Learning and Optimization for Influence Maximization

1 code implementation1 May 2023 Chen Ling, Junji Jiang, Junxiang Wang, My Thai, Lukas Xue, James Song, Meikang Qiu, Liang Zhao

Influence maximization (IM) is formulated as selecting a set of initial users from a social network to maximize the expected number of influenced users.

Graph Representation Learning

Molecular Design Based on Integer Programming and Splitting Data Sets by Hyperplanes

no code implementations27 Apr 2023 Jianshen Zhu, Naveed Ahmed Azam, Kazuya Haraguchi, Liang Zhao, Hiroshi Nagamochi, Tatsuya Akutsu

A novel framework for designing the molecular structure of chemical compounds with a desired chemical property has recently been proposed.

Prediction

Dealing With Heterogeneous 3D MR Knee Images: A Federated Few-Shot Learning Method With Dual Knowledge Distillation

1 code implementation25 Mar 2023 Xiaoxiao He, Chaowei Tan, Bo Liu, Liping Si, Weiwu Yao, Liang Zhao, Di Liu, Qilong Zhangli, Qi Chang, Kang Li, Dimitris N. Metaxas

The supervised learning of the proposed method extracts features from limited labeled data in each client, while the unsupervised data is used to distill both feature and response-based knowledge from a national data repository to further improve the accuracy of the collaborative model and reduce the communication cost.

Federated Learning Few-Shot Learning +1