Search Results for author: Xiang Li

Found 446 papers, 173 papers with code

JointCL: A Joint Contrastive Learning Framework for Zero-Shot Stance Detection

1 code implementation ACL 2022 Bin Liang, Qinglin Zhu, Xiang Li, Min Yang, Lin Gui, Yulan He, Ruifeng Xu

In this paper, we propose a joint contrastive learning (JointCL) framework, which consists of stance contrastive learning and target-aware prototypical graph contrastive learning.

Contrastive Learning Zero-Shot Stance Detection

Gait Recognition from a Single Image using a Phase-Aware Gait Cycle Reconstruction Network

no code implementations ECCV 2020 Chi Xu, Yasushi Makihara, Xiang Li, Yasushi Yagi, Jianfeng Lu

Specifically, a phase estimation network is introduced for the input single image, and the gait cycle reconstruction network exploits the estimated phase to mitigate the dependence of an encoded feature on the phase of that single image.

Gait Recognition

Towards Robust Neural Machine Translation with Iterative Scheduled Data-Switch Training

1 code implementation COLING 2022 Zhongjian Miao, Xiang Li, Liyan Kang, Wen Zhang, Chulun Zhou, Yidong Chen, Bin Wang, Min Zhang, Jinsong Su

Most existing methods on robust neural machine translation (NMT) construct adversarial examples by injecting noise into authentic examples and indiscriminately exploit two types of examples.

Machine Translation NMT +2

融合情感分析的隐式反问句识别模型(Implicit Rhetorical Questions Recognition Model Combined with Sentiment Analysis)

no code implementations CCL 2021 Xiang Li, Chengwei Liu, Xiaoxu Zhu

“反问是现代汉语中一种常用的修辞手法, 根据是否含有反问标记可分为显式反问句与隐式反问句。其中隐式反问句表达的情感更为丰富, 表现形式也十分复杂, 对隐式反问句的识别更具挑战性。本文首先扩充了汉语反问句语料库, 语料库规模达到10000余句, 接着针对隐式反问句的特点, 提出了一种融合情感分析的隐式反问句识别模型。模型考虑了句子的语义信息, 上下文信息, 并借助情感分析任务辅助识别隐式反问句。实验结果表明, 本文提出的模型在隐式反问句识别任务上取得了良好的性能。”

Sentiment Analysis

BIT-Xiaomi’s System for AutoSimTrans 2022

no code implementations NAACL (AutoSimTrans) 2022 Mengge Liu, Xiang Li, Bao Chen, Yanzhi Tian, Tianwei Lan, Silin Li, Yuhang Guo, Jian Luan, Bin Wang

This system paper describes the BIT-Xiaomi simultaneous translation system for Autosimtrans 2022 simultaneous translation challenge.

Chunking Data Augmentation +1

Multi-Modal Sarcasm Detection via Cross-Modal Graph Convolutional Network

1 code implementation ACL 2022 Bin Liang, Chenwei Lou, Xiang Li, Min Yang, Lin Gui, Yulan He, Wenjie Pei, Ruifeng Xu

Then, the descriptions of the objects are served as a bridge to determine the importance of the association between the objects of image modality and the contextual words of text modality, so as to build a cross-modal graph for each multi-modal instance.

Sarcasm Detection

Understanding Long Videos in One Multimodal Language Model Pass

1 code implementation25 Mar 2024 Kanchana Ranasinghe, Xiang Li, Kumara Kahatapitiya, Michael S. Ryoo

In addition to faster inference, we discover the resulting models to yield surprisingly good accuracy on long-video tasks, even with no video specific information.

Fine-grained Action Recognition Language Modelling +3

A Survey of Neural Code Intelligence: Paradigms, Advances and Beyond

1 code implementation21 Mar 2024 Qiushi Sun, Zhirui Chen, Fangzhi Xu, Kanzhi Cheng, Chang Ma, Zhangyue Yin, Jianing Wang, Chengcheng Han, Renyu Zhu, Shuai Yuan, Qipeng Guo, Xipeng Qiu, Pengcheng Yin, XiaoLi Li, Fei Yuan, Lingpeng Kong, Xiang Li, Zhiyong Wu

Building on our examination of the developmental trajectories, we further investigate the emerging synergies between code intelligence and broader machine intelligence, uncovering new cross-domain opportunities and illustrating the substantial influence of code intelligence across various domains.

Few-shot Oriented Object Detection with Memorable Contrastive Learning in Remote Sensing Images

no code implementations20 Mar 2024 Jiawei Zhou, Wuzhou Li, Yi Cao, Hongtao Cai, Xiang Li

Few-shot object detection (FSOD) has garnered significant research attention in the field of remote sensing due to its ability to reduce the dependency on large amounts of annotated data.

Contrastive Learning Few-Shot Object Detection +3

Eye-gaze Guided Multi-modal Alignment Framework for Radiology

no code implementations19 Mar 2024 Chong Ma, Hanqi Jiang, WenTing Chen, Zihao Wu, Xiaowei Yu, Fang Zeng, Lei Guo, Dajiang Zhu, Tuo Zhang, Dinggang Shen, Tianming Liu, Xiang Li

Additionally, we explore the impact of varying amounts of eye-gaze data on model performance, highlighting the feasibility and utility of integrating this auxiliary data into multi-modal pre-training.

Zero-Shot Learning

Context-based Fast Recommendation Strategy for Long User Behavior Sequence in Meituan Waimai

no code implementations19 Mar 2024 Zhichao Feng, Junjiie Xie, Kaiyuan Li, Yu Qin, Pengfei Wang, Qianzhong Li, Bin Yin, Xiang Li, Wei Lin, Shangguang Wang

We first identify contexts that share similar user preferences with the target context and then locate the corresponding PoIs based on these identified contexts.

Sequential Recommendation

AlphaFin: Benchmarking Financial Analysis with Retrieval-Augmented Stock-Chain Framework

1 code implementation19 Mar 2024 Xiang Li, Zhenyu Li, Chen Shi, Yong Xu, Qing Du, Mingkui Tan, Jun Huang, Wei Lin

The task of financial analysis primarily encompasses two key areas: stock trend prediction and the corresponding financial question answering.

Benchmarking Question Answering +2

Dual-Channel Multiplex Graph Neural Networks for Recommendation

no code implementations18 Mar 2024 Xiang Li, Chaofan Fu, Zhongying Zhao, Guanjie Zheng, Chao Huang, Junyu Dong, Yanwei Yu

Nevertheless, these approaches still grapple with two significant shortcomings: (1) Insufficient modeling and exploitation of the impact of various behavior patterns formed by multiplex relations between users and items on representation learning, and (2) ignoring the effect of different relations in the behavior patterns on the target relation in recommender system scenarios.

Recommendation Systems Relation +1

LSKNet: A Foundation Lightweight Backbone for Remote Sensing

1 code implementation18 Mar 2024 YuXuan Li, Xiang Li, Yimain Dai, Qibin Hou, Li Liu, Yongxiang Liu, Ming-Ming Cheng, Jian Yang

While a considerable amount of research has been dedicated to remote sensing classification, object detection and semantic segmentation, most of these studies have overlooked the valuable prior knowledge embedded within remote sensing scenarios.

object-detection Object Detection +1

Don't Half-listen: Capturing Key-part Information in Continual Instruction Tuning

no code implementations15 Mar 2024 Yongquan He, Xuancheng Huang, Minghao Tang, Lingxun Meng, Xiang Li, Wei Lin, Wenyuan Zhang, Yifu Gao

Recent methods try to alleviate the CF problem by modifying models or replaying data, which may only remember the surface-level pattern of instructions and get confused on held-out tasks.

Instruction Following

Cardiac Magnetic Resonance 2D+T Short- and Long-axis Segmentation via Spatio-temporal SAM Adaptation

no code implementations15 Mar 2024 Zhennong Chen, Sekeun Kim, Hui Ren, Quanzheng Li, Xiang Li

Accurate 2D+T myocardium segmentation in cine cardiac magnetic resonance (CMR) scans is essential to analyze LV motion throughout the cardiac cycle comprehensively.

Myocardium Segmentation Segmentation +1

MonoOcc: Digging into Monocular Semantic Occupancy Prediction

1 code implementation13 Mar 2024 Yupeng Zheng, Xiang Li, Pengfei Li, Yuhang Zheng, Bu Jin, Chengliang Zhong, Xiaoxiao Long, Hao Zhao, Qichao Zhang

However, existing methods rely on a complex cascaded framework with relatively limited information to restore 3D scenes, including a dependency on supervision solely on the whole network's output, single-frame input, and the utilization of a small backbone.

Autonomous Vehicles

KnowCoder: Coding Structured Knowledge into LLMs for Universal Information Extraction

no code implementations12 Mar 2024 Zixuan Li, Yutao Zeng, Yuxin Zuo, Weicheng Ren, Wenxuan Liu, Miao Su, Yucan Guo, Yantao Liu, Xiang Li, Zhilei Hu, Long Bai, Wei Li, Yidan Liu, Pan Yang, Xiaolong Jin, Jiafeng Guo, Xueqi Cheng

After instruction tuning, KnowCoder further exhibits strong generalization ability on unseen schemas and achieves up to $\textbf{12. 5%}$ and $\textbf{21. 9%}$, compared to sota baselines, under the zero-shot setting and the low resource setting, respectively.

Code Generation Language Modelling +2

Medical Image Synthesis via Fine-Grained Image-Text Alignment and Anatomy-Pathology Prompting

no code implementations11 Mar 2024 WenTing Chen, Pengyu Wang, Hui Ren, Lichao Sun, Quanzheng Li, Yixuan Yuan, Xiang Li

To address these challenges, we propose a novel medical image synthesis model that leverages fine-grained image-text alignment and anatomy-pathology prompts to generate highly detailed and accurate synthetic medical images.

Anatomy Descriptive +1

SARDet-100K: Towards Open-Source Benchmark and ToolKit for Large-Scale SAR Object Detection

1 code implementation11 Mar 2024 YuXuan Li, Xiang Li, Weijie Li, Qibin Hou, Li Liu, Ming-Ming Cheng, Jian Yang

To the best of our knowledge, SARDet-100K is the first COCO-level large-scale multi-class SAR object detection dataset ever created.

 Ranked #1 on 2D Object Detection on SARDet-100K (using extra training data)

Object object-detection +1

Conditional Score-Based Diffusion Model for Cortical Thickness Trajectory Prediction

no code implementations11 Mar 2024 Qing Xiao, Siyeop Yoon, Hui Ren, Matthew Tivnan, Lichao Sun, Quanzheng Li, Tianming Liu, Yu Zhang, Xiang Li

Alzheimer's Disease (AD) is a neurodegenerative condition characterized by diverse progression rates among individuals, with changes in cortical thickness (CTh) closely linked to its progression.

Trajectory Prediction

Decoupled Data Consistency with Diffusion Purification for Image Restoration

no code implementations10 Mar 2024 Xiang Li, Soo Min Kwon, Ismail R. Alkhouri, Saiprasad Ravishankar, Qing Qu

To solve image restoration problems, many existing techniques achieve data consistency by incorporating additional likelihood gradient steps into the reverse sampling process of diffusion models.

Deblurring Image Denoising +2

$\text{R}^2$-Bench: Benchmarking the Robustness of Referring Perception Models under Perturbations

2 code implementations7 Mar 2024 Xiang Li, Kai Qiu, Jinglu Wang, Xiaohao Xu, Rita Singh, Kashu Yamazak, Hao Chen, Xiaonan Huang, Bhiksha Raj

Referring perception, which aims at grounding visual objects with multimodal referring guidance, is essential for bridging the gap between humans, who provide instructions, and the environment where intelligent systems perceive.

Benchmarking

A Survey on Applications of Reinforcement Learning in Spatial Resource Allocation

no code implementations6 Mar 2024 Di Zhang, Moyang Wang, Joseph Mango, Xiang Li, Xianrui Xu

Given these advancements, there has been a surge in novel methods employing reinforcement learning to tackle spatial resource allocation problems.

Decision Making reinforcement-learning

PromptKD: Unsupervised Prompt Distillation for Vision-Language Models

1 code implementation5 Mar 2024 Zheng Li, Xiang Li, Xinyi Fu, Xin Zhang, Weiqiang Wang, Shuo Chen, Jian Yang

To our best knowledge, we are the first to (1) perform unsupervised domain-specific prompt-driven knowledge distillation for CLIP, and (2) establish a practical pre-storing mechanism of text features as shared class vectors between teacher and student.

Knowledge Distillation Prompt Engineering +1

Not all Layers of LLMs are Necessary during Inference

no code implementations4 Mar 2024 Siqi Fan, Xin Jiang, Xiang Li, Xuying Meng, Peng Han, Shuo Shang, Aixin Sun, Yequan Wang, Zhongyuan Wang

To answer this question, we first indicate that Not all Layers are Necessary during Inference by statistically analyzing the activated layers across tasks.

In-Context Learning

Dual-Granularity Medication Recommendation Based on Causal Inference

no code implementations1 Mar 2024 Shunpan Liang, Xiang Li, Chen Li, Yu Lei, Yulei Hou, Tengfei Ma

Medication recommendation aims to integrate patients' long-term health records with medical knowledge, recommending accuracy and safe medication combinations for specific conditions.

Causal Inference Recommendation Systems

StaPep: an open-source tool for the structure prediction and feature extraction of hydrocarbon-stapled peptides

1 code implementation28 Feb 2024 Zhe Wang, Jianping Wu, Mengjun Zheng, Chenchen Geng, Borui Zhen, Wei zhang, Hui Wu, Zhengyang Xu, Gang Xu, Si Chen, Xiang Li

Many tools exist for extracting structural and physiochemical descriptors from linear peptides to predict their properties, but similar tools for hydrocarbon-stapled peptides are lacking. Here, we present StaPep, a Python-based toolkit designed for generating 2D/3D structures and calculating 21 distinct features for hydrocarbon-stapled peptides. The current version supports hydrocarbon-stapled peptides containing 2 non-standard amino acids (norleucine and 2-aminoisobutyric acid) and 6 nonnatural anchoring residues (S3, S5, S8, R3, R5 and R8). Then we established a hand-curated dataset of 201 hydrocarbon-stapled peptides and 384 linear peptides with sequence information and experimental membrane permeability, to showcase StaPep's application in artificial intelligence projects. A machine learning-based predictor utilizing above calculated features was developed with AUC of 0. 85, for identifying cell-penetrating hydrocarbon-stapled peptides. StaPep's pipeline spans data retrieval, cleaning, structure generation, molecular feature calculation, and machine learning model construction for hydrocarbon-stapled peptides. The source codes and dataset are freely available on Github: https://github. com/dahuilangda/stapep_package.

Retrieval

TreeEval: Benchmark-Free Evaluation of Large Language Models through Tree Planning

1 code implementation20 Feb 2024 Xiang Li, Yunshi Lan, Chao Yang

Recently, numerous new benchmarks have been established to evaluate the performance of large language models (LLMs) via either computing a holistic score or employing another LLM as a judge.

Question Generation Question-Generation

A Literature Review of Literature Reviews in Pattern Analysis and Machine Intelligence

no code implementations20 Feb 2024 Penghai Zhao, Xin Zhang, Ming-Ming Cheng, Jian Yang, Xiang Li

To improve efficiency, this paper aims to provide a thorough review of reviews in the PAMI field from diverse perspectives.

Language Modelling Large Language Model

Visual In-Context Learning for Large Vision-Language Models

no code implementations18 Feb 2024 Yucheng Zhou, Xiang Li, Qianning Wang, Jianbing Shen

In Large Visual Language Models (LVLMs), the efficacy of In-Context Learning (ICL) remains limited by challenges in cross-modal interactions and representation disparities.

In-Context Learning Position +2

AutoPRM: Automating Procedural Supervision for Multi-Step Reasoning via Controllable Question Decomposition

no code implementations18 Feb 2024 Zhaorun Chen, Zhuokai Zhao, Zhihong Zhu, Ruiqi Zhang, Xiang Li, Bhiksha Raj, Huaxiu Yao

Recent advancements in large language models (LLMs) have shown promise in multi-step reasoning tasks, yet their reliance on extensive manual labeling to provide procedural feedback remains a significant impediment.

Reasoning before Comparison: LLM-Enhanced Semantic Similarity Metrics for Domain Specialized Text Analysis

no code implementations17 Feb 2024 Shaochen Xu, Zihao Wu, Huaqin Zhao, Peng Shu, Zhengliang Liu, Wenxiong Liao, Sheng Li, Andrea Sikora, Tianming Liu, Xiang Li

In this study, we leverage LLM to enhance the semantic analysis and develop similarity metrics for texts, addressing the limitations of traditional unsupervised NLP metrics like ROUGE and BLEU.

Semantic Similarity Semantic Textual Similarity +1

Evaluating and Improving Continual Learning in Spoken Language Understanding

no code implementations16 Feb 2024 Muqiao Yang, Xiang Li, Umberto Cappellazzo, Shinji Watanabe, Bhiksha Raj

In this work, we propose an evaluation methodology that provides a unified evaluation on stability, plasticity, and generalizability in continual learning.

Continual Learning Spoken Language Understanding

Class-Balanced and Reinforced Active Learning on Graphs

no code implementations15 Feb 2024 Chengcheng Yu, Jiapeng Zhu, Xiang Li

It learns an optimal policy to acquire class-balanced and informative nodes for annotation, maximizing the performance of GNNs trained with selected labeled nodes.

Active Learning Graph Classification +2

Customizable Perturbation Synthesis for Robust SLAM Benchmarking

1 code implementation12 Feb 2024 Xiaohao Xu, Tianyi Zhang, Sibo Wang, Xiang Li, Yongqi Chen, Ye Li, Bhiksha Raj, Matthew Johnson-Roberson, Xiaonan Huang

To this end, we propose a novel, customizable pipeline for noisy data synthesis, aimed at assessing the resilience of multi-modal SLAM models against various perturbations.

Benchmarking Simultaneous Localization and Mapping

A General Framework for Learning from Weak Supervision

1 code implementation2 Feb 2024 Hao Chen, Jindong Wang, Lei Feng, Xiang Li, Yidong Wang, Xing Xie, Masashi Sugiyama, Rita Singh, Bhiksha Raj

Weakly supervised learning generally faces challenges in applicability to various scenarios with diverse weak supervision and in scalability due to the complexity of existing algorithms, thereby hindering the practical deployment.

Weakly-supervised Learning

PepGB: Facilitating peptide drug discovery via graph neural networks

no code implementations26 Jan 2024 Yipin Lei, Xu Wang, Meng Fang, Han Li, Xiang Li, Jianyang Zeng

In summary, our proposed frameworks can serve as potent tools to facilitate peptide early drug discovery.

Contrastive Learning Drug Discovery

The Radiation Oncology NLP Database

1 code implementation19 Jan 2024 Zhengliang Liu, Jason Holmes, Wenxiong Liao, Chenbin Liu, Lian Zhang, Hongying Feng, Peilong Wang, Muhammad Ali Elahi, Hongmin Cai, Lichao Sun, Quanzheng Li, Xiang Li, Tianming Liu, Jiajian Shen, Wei Liu

ROND is specifically designed to address this gap in the domain of radiation oncology, a field that offers many opportunities for NLP exploration.

Language Modelling Large Language Model +7

VIPTR: A Vision Permutable Extractor for Fast and Efficient Scene Text Recognition

1 code implementation18 Jan 2024 Xianfu Cheng, Weixiao Zhou, Xiang Li, Xiaoming Chen, Jian Yang, Tongliang Li, Zhoujun Li

In this work, we propose the VIsion Permutable extractor for fast and efficient scene Text Recognition (VIPTR), which achieves an impressive balance between high performance and rapid inference speeds in the domain of STR.

Scene Text Recognition

Learning from Graphs with Heterophily: Progress and Future

1 code implementation18 Jan 2024 Chenghua Gong, Yao Cheng, Xiang Li, Caihua Shan, Siqiang Luo

Graphs are structured data that models complex relations between real-world entities.

Graph Learning

Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Security

2 code implementations10 Jan 2024 Yuanchun Li, Hao Wen, Weijun Wang, Xiangyu Li, Yizhen Yuan, Guohong Liu, Jiacheng Liu, Wenxing Xu, Xiang Wang, Yi Sun, Rui Kong, Yile Wang, Hanfei Geng, Jian Luan, Xuefeng Jin, Zilong Ye, Guanjing Xiong, Fan Zhang, Xiang Li, Mengwei Xu, Zhijun Li, Peng Li, Yang Liu, Ya-Qin Zhang, Yunxin Liu

Next, we discuss several key challenges to achieve intelligent, efficient and secure Personal LLM Agents, followed by a comprehensive survey of representative solutions to address these challenges.

Large Language Models for Robotics: Opportunities, Challenges, and Perspectives

no code implementations9 Jan 2024 Jiaqi Wang, Zihao Wu, Yiwei Li, Hanqi Jiang, Peng Shu, Enze Shi, Huawen Hu, Chong Ma, Yiheng Liu, Xuhui Wang, Yincheng Yao, Xuan Liu, Huaqin Zhao, Zhengliang Liu, Haixing Dai, Lin Zhao, Bao Ge, Xiang Li, Tianming Liu, Shu Zhang

Notably, in the realm of robot task planning, LLMs harness their advanced reasoning and language comprehension capabilities to formulate precise and efficient action plans based on natural language instructions.

Robot Task Planning

Finite-Time Decoupled Convergence in Nonlinear Two-Time-Scale Stochastic Approximation

no code implementations8 Jan 2024 Yuze Han, Xiang Li, Zhihua Zhang

In two-time-scale stochastic approximation (SA), two iterates are updated at varying speeds using different step sizes, with each update influencing the other.

Null Space Properties of Neural Networks with Applications to Image Steganography

no code implementations1 Jan 2024 Xiang Li, Kevin M. Short

Through experiments on image datasets such as MNIST, we show that we can use null space components to force the neural network to choose a selected hidden image class, even though the overall image can be made to look like a completely different image.

Image Steganography

In-Hand 3D Object Reconstruction from a Monocular RGB Video

no code implementations27 Dec 2023 Shijian Jiang, Qi Ye, Rengan Xie, Yuchi Huo, Xiang Li, Yang Zhou, Jiming Chen

We evaluate our approach on HO3D and HOD datasets and demonstrate that it outperforms the state-of-the-art methods in terms of reconstruction surface quality, with an improvement of $52\%$ on HO3D and $20\%$ on HOD.

3D Object Reconstruction 3D Reconstruction +2

Fine-Grained Image-Text Alignment in Medical Imaging Enables Cyclic Image-Report Generation

no code implementations13 Dec 2023 WenTing Chen, Linlin Shen, Xiang Li, Yixuan Yuan

To address these issues, we propose a novel Adaptive patch-word Matching (AdaMatch) model to correlate chest X-ray (CXR) image regions with words in medical reports and apply it to CXR-report generation to provide explainability for the generation process.

Language Modelling Large Language Model

Context Matters: Data-Efficient Augmentation of Large Language Models for Scientific Applications

1 code implementation12 Dec 2023 Xiang Li, Haoran Tang, Siyu Chen, Ziwei Wang, Anurag Maravi, Marcin Abram

In this paper, we explore the challenges inherent to Large Language Models (LLMs) like GPT-4, particularly their propensity for hallucinations, logic mistakes, and incorrect conclusions when tasked with answering complex questions.

Diffusion Illusions: Hiding Images in Plain Sight

no code implementations6 Dec 2023 Ryan Burgert, Xiang Li, Abe Leite, Kanchana Ranasinghe, Michael S. Ryoo

We explore the problem of computationally generating special `prime' images that produce optical illusions when physically arranged and viewed in a certain way.

Probabilistic Copyright Protection Can Fail for Text-to-Image Generative Models

1 code implementation29 Nov 2023 Xiang Li, Qianli Shen, Kenji Kawaguchi

The booming use of text-to-image generative models has raised concerns about their high risk of producing copyright-infringing content.

Federated Learning via Consensus Mechanism on Heterogeneous Data: A New Perspective on Convergence

1 code implementation21 Nov 2023 Shu Zheng, Tiandi Ye, Xiang Li, Ming Gao

We theoretically show that the consensus mechanism can guarantee the convergence of the global objective.

Fairness Federated Learning

Jailbreaking GPT-4V via Self-Adversarial Attacks with System Prompts

no code implementations15 Nov 2023 Yuanwei Wu, Xiang Li, Yixin Liu, Pan Zhou, Lichao Sun

This finding indicates potential exploitable security risks in MLLMs; 2) Based on the acquired system prompts, we propose a novel MLLM jailbreaking attack method termed SASP (Self-Adversarial Attack via System Prompt).

Adversarial Attack

Knowledge Graph Construction in Power Distribution Networks

no code implementations15 Nov 2023 Xiang Li, Che Wang, Bing Li, Hao Chen, Sizhe Li

In this paper, we propose a method for knowledge graph construction in power distribution networks.

Entity Linking graph construction +1

Self-supervised Heterogeneous Graph Variational Autoencoders

no code implementations14 Nov 2023 Yige Zhao, Jianxiang Yu, Yao Cheng, Chengcheng Yu, Yiding Liu, Xiang Li, Shuaiqiang Wang

Instead of directly reconstructing raw features for attributed nodes, SHAVA generates the initial low-dimensional representation matrix for all the nodes, based on which raw features of attributed nodes are further reconstructed to leverage accurate attributes.

Attribute Graph Mining

u-LLaVA: Unifying Multi-Modal Tasks via Large Language Model

1 code implementation9 Nov 2023 Jinjin Xu, Liwu Xu, Yuzhe Yang, Xiang Li, Fanyi Wang, Yanchun Xie, Yi-Jie Huang, Yaqian Li

Recent advancements in multi-modal large language models (MLLMs) have led to substantial improvements in visual understanding, primarily driven by sophisticated modality alignment strategies.

Instruction Following Language Modelling +1

High-resolution power equipment recognition based on improved self-attention

no code implementations6 Nov 2023 Siyi Zhang, Cheng Liu, Xiang Li, Xin Zhai, Zhen Wei, Sizhe Li, Xun Ma

The current trend of automating inspections at substations has sparked a surge in interest in the field of transformer image recognition.

Region Proposal

Parameter-Agnostic Optimization under Relaxed Smoothness

no code implementations6 Nov 2023 Florian Hübler, Junchi Yang, Xiang Li, Niao He

However, as the assumption is relaxed to the more realistic $(L_0, L_1)$-smoothness, all existing convergence results still necessitate tuning of the stepsize.

Exploiting Latent Attribute Interaction with Transformer on Heterogeneous Information Networks

no code implementations6 Nov 2023 Zeyuan Zhao, Qingqing Ge, Anfeng Cheng, Yiding Liu, Xiang Li, Shuaiqiang Wang

In addition, most of them only consider the interactions between nodes while neglecting the high-order information behind the latent interactions among different node features.

Attribute

Prioritized Propagation in Graph Neural Networks

no code implementations6 Nov 2023 Yao Cheng, Minjie Chen, Xiang Li, Caihua Shan, Ming Gao

Specifically, the framework consists of three components: a backbone GNN model, a propagation controller to determine the optimal propagation steps for nodes, and a weight controller to compute the priority scores for nodes.

Retrieval-Augmented Code Generation for Universal Information Extraction

no code implementations6 Nov 2023 Yucan Guo, Zixuan Li, Xiaolong Jin, Yantao Liu, Yutao Zeng, Wenxuan Liu, Xiang Li, Pan Yang, Long Bai, Jiafeng Guo, Xueqi Cheng

Therefore, in this paper, we propose a universal retrieval-augmented code generation framework based on LLMs, called Code4UIE, for IE tasks.

Code Generation In-Context Learning +1

Resist Label Noise with PGM for Graph Neural Networks

no code implementations3 Nov 2023 Qingqing Ge, Jianxiang Yu, Zeyuan Zhao, Xiang Li

To further leverage the information of clean labels in the noisy label set, we put forward LNP-v2, which incorporates the noisy label set into the Bayesian network to generate clean labels.

Limited Data, Unlimited Potential: A Study on ViTs Augmented by Masked Autoencoders

1 code implementation31 Oct 2023 Srijan Das, Tanmay Jain, Dominick Reilly, Pranav Balaji, Soumyajit Karmakar, Shyam Marjit, Xiang Li, Abhijit Das, Michael S. Ryoo

We explore the appropriate SSL tasks that can be optimized alongside the primary task, the training schemes for these tasks, and the data scale at which they can be most effective.

DeepFake Detection Face Swapping +1

Multimodal ChatGPT for Medical Applications: an Experimental Study of GPT-4V

1 code implementation29 Oct 2023 Zhiling Yan, Kai Zhang, Rong Zhou, Lifang He, Xiang Li, Lichao Sun

In this paper, we critically evaluate the capabilities of the state-of-the-art multimodal large language model, i. e., GPT-4 with Vision (GPT-4V), on Visual Question Answering (VQA) task.

Language Modelling Large Language Model +2

3DCoMPaT$^{++}$: An improved Large-scale 3D Vision Dataset for Compositional Recognition

1 code implementation27 Oct 2023 Habib Slim, Xiang Li, Yuchen Li, Mahmoud Ahmed, Mohamed Ayman, Ujjwal Upadhyay, Ahmed Abdelreheem, Arpit Prajapati, Suhail Pothigara, Peter Wonka, Mohamed Elhoseiny

In this work, we present 3DCoMPaT$^{++}$, a multimodal 2D/3D dataset with 160 million rendered views of more than 10 million stylized 3D shapes carefully annotated at the part-instance level, alongside matching RGB point clouds, 3D textured meshes, depth maps, and segmentation masks.

Label Propagation for Graph Label Noise

no code implementations25 Oct 2023 Yao Cheng, Caihua Shan, Yifei Shen, Xiang Li, Siqiang Luo, Dongsheng Li

In this paper, we study graph label noise in the context of arbitrary heterophily, with the aim of rectifying noisy labels and assigning labels to previously unlabeled nodes.

Denoising Node Classification

Zone Evaluation: Revealing Spatial Bias in Object Detection

1 code implementation20 Oct 2023 Zhaohui Zheng, Yuming Chen, Qibin Hou, Xiang Li, Ping Wang, Ming-Ming Cheng

A fundamental limitation of object detectors is that they suffer from "spatial bias", and in particular perform less satisfactorily when detecting objects near image borders.

Object object-detection +1

Uncertainty-aware Parameter-Efficient Self-training for Semi-supervised Language Understanding

1 code implementation19 Oct 2023 Jianing Wang, Qiushi Sun, Nuo Chen, Chengyu Wang, Jun Huang, Ming Gao, Xiang Li

The recent success of large pre-trained language models (PLMs) heavily hinges on massive labeled data, which typically produces inferior performance in low-resource scenarios.

Prompt Tuning for Multi-View Graph Contrastive Learning

no code implementations16 Oct 2023 Chenghua Gong, Xiang Li, Jianxiang Yu, Cheng Yao, Jiaqi Tan, Chengcheng Yu, Dawei Yin

Third, we design a prompting tuning method for our multi-view graph contrastive learning method to bridge the gap between pretexts and downsteam tasks.

Contrastive Learning

Empower Text-Attributed Graphs Learning with Large Language Models (LLMs)

no code implementations15 Oct 2023 Jianxiang Yu, Yuxiang Ren, Chenghua Gong, Jiaqi Tan, Xiang Li, Xuecang Zhang

In order to tackle this challenge, we propose a lightweight paradigm called ENG, which adopts a plug-and-play approach to empower text-attributed graphs through node generation using LLMs.

Few-Shot Learning Graph Learning +3

DropMix: Better Graph Contrastive Learning with Harder Negative Samples

1 code implementation15 Oct 2023 Yueqi Ma, Minjie Chen, Xiang Li

Recently, Mixup has been introduced to synthesize hard negative samples in graph contrastive learning (GCL).

Contrastive Learning

MiniGPT-v2: large language model as a unified interface for vision-language multi-task learning

1 code implementation14 Oct 2023 Jun Chen, Deyao Zhu, Xiaoqian Shen, Xiang Li, Zechun Liu, Pengchuan Zhang, Raghuraman Krishnamoorthi, Vikas Chandra, Yunyang Xiong, Mohamed Elhoseiny

Motivated by this, we target to build a unified interface for completing many vision-language tasks including image description, visual question answering, and visual grounding, among others.

Language Modelling Large Language Model +4

Context-aware Session-based Recommendation with Graph Neural Networks

1 code implementation14 Oct 2023 Zhihui Zhang, Jianxiang Yu, Xiang Li

Session-based recommendation (SBR) is a task that aims to predict items based on anonymous sequences of user behaviors in a session.

Session-Based Recommendations

DialCoT Meets PPO: Decomposing and Exploring Reasoning Paths in Smaller Language Models

1 code implementation8 Oct 2023 Chengcheng Han, Xiaowei Du, Che Zhang, Yixin Lian, Xiang Li, Ming Gao, Baoyuan Wang

Chain-of-Thought (CoT) prompting has proven to be effective in enhancing the reasoning capabilities of Large Language Models (LLMs) with at least 100 billion parameters.

Arithmetic Reasoning

Uncertainty Quantification in Inverse Models in Hydrology

no code implementations3 Oct 2023 Somya Sharma Chatterjee, Rahul Ghosh, Arvind Renganathan, Xiang Li, Snigdhansu Chatterjee, John Nieber, Christopher Duffy, Vipin Kumar

Our inverse model offers 3\% improvement in R$^2$ for the inverse model (basin characteristic estimation) and 6\% for the forward model (streamflow prediction).

Uncertainty Quantification

Completing Visual Objects via Bridging Generation and Segmentation

no code implementations1 Oct 2023 Xiang Li, Yinpeng Chen, Chung-Ching Lin, Hao Chen, Kai Hu, Rita Singh, Bhiksha Raj, Lijuan Wang, Zicheng Liu

This paper presents a novel approach to object completion, with the primary goal of reconstructing a complete object from its partially visible components.

Image Generation Object +1

Corex: Pushing the Boundaries of Complex Reasoning through Multi-Model Collaboration

1 code implementation30 Sep 2023 Qiushi Sun, Zhangyue Yin, Xiang Li, Zhiyong Wu, Xipeng Qiu, Lingpeng Kong

Large Language Models (LLMs) are evolving at an unprecedented pace and have exhibited considerable capability in the realm of natural language processing (NLP) with world knowledge.

World Knowledge

Towards Robust Audiovisual Segmentation in Complex Environments with Quantization-based Semantic Decomposition

3 code implementations29 Sep 2023 Xiang Li, Jinglu Wang, Xiaohao Xu, Xiulian Peng, Rita Singh, Yan Lu, Bhiksha Raj

We propose a semantic decomposition method based on product quantization, where the multi-source semantics can be decomposed and represented by several disentangled and noise-suppressed single-source semantics.

Quantization

Generating Personalized Insulin Treatments Strategies with Deep Conditional Generative Time Series Models

no code implementations28 Sep 2023 Manuel Schürch, Xiang Li, Ahmed Allam, Giulia Rathmes, Amina Mollaysa, Claudia Cavelti-Weder, Michael Krauthammer

We propose a novel framework that combines deep generative time series models with decision theory for generating personalized treatment strategies.

Time Series

MedEdit: Model Editing for Medical Question Answering with External Knowledge Bases

no code implementations27 Sep 2023 Yucheng Shi, Shaochen Xu, Zhengliang Liu, Tianming Liu, Xiang Li, Ninghao Liu

Focusing on medical QA using the MedQA-SMILE dataset, we evaluate the impact of different retrieval models and the number of facts provided to the LLM.

In-Context Learning Model Editing +2

AutoPrep: An Automatic Preprocessing Framework for In-the-Wild Speech Data

no code implementations25 Sep 2023 Jianwei Yu, Hangting Chen, Yanyao Bian, Xiang Li, Yi Luo, Jinchuan Tian, Mengyang Liu, Jiayi Jiang, Shuai Wang

To address this issue, we introduce an automatic in-the-wild speech data preprocessing framework (AutoPrep) in this paper, which is designed to enhance speech quality, generate speaker labels, and produce transcriptions automatically.

Automatic Speech Recognition Speech Enhancement +3

MediViSTA-SAM: Zero-shot Medical Video Analysis with Spatio-temporal SAM Adaptation

1 code implementation24 Sep 2023 Sekeun Kim, Kyungsang Kim, Jiang Hu, Cheng Chen, Zhiliang Lyu, Ren Hui, Sunghwan Kim, Zhengliang Liu, Aoxiao Zhong, Xiang Li, Tianming Liu, Quanzheng Li

The Segmentation Anything Model (SAM) has attracted considerable attention as a foundational model well-known for its robust generalization capabilities across various downstream tasks.

Segmentation Video Segmentation +1

Asca: less audio data is more insightful

1 code implementation23 Sep 2023 Xiang Li, JunHao Chen, Chao Li, Hongwu Lv

Audio recognition in specialized areas such as birdsong and submarine acoustics faces challenges in large-scale pre-training due to the limitations in available samples imposed by sampling environments and specificity requirements.

Specificity

Invisible Watermarking for Audio Generation Diffusion Models

2 code implementations22 Sep 2023 Xirong Cao, Xiang Li, Divyesh Jadav, Yanzhao Wu, Zhehui Chen, Chen Zeng, Wenqi Wei

Diffusion models have gained prominence in the image domain for their capabilities in data generation and transformation, achieving state-of-the-art performance in various tasks in both image and audio domains.

Audio Generation

A Discourse-level Multi-scale Prosodic Model for Fine-grained Emotion Analysis

no code implementations21 Sep 2023 Xianhao Wei, Jia Jia, Xiang Li, Zhiyong Wu, Ziyi Wang

More interestingly, although we aim at the synthesis effect of the style transfer model, the synthesized speech by the proposed text prosodic analysis model is even better than the style transfer from the original speech in some user evaluation indicators.

Emotion Recognition Speech Synthesis +1

MA-SAM: Modality-agnostic SAM Adaptation for 3D Medical Image Segmentation

1 code implementation16 Sep 2023 Cheng Chen, Juzheng Miao, Dufan Wu, Zhiling Yan, Sekeun Kim, Jiang Hu, Aoxiao Zhong, Zhengliang Liu, Lichao Sun, Xiang Li, Tianming Liu, Pheng-Ann Heng, Quanzheng Li

The Segment Anything Model (SAM), a foundation model for general image segmentation, has demonstrated impressive zero-shot performance across numerous natural image segmentation tasks.

Image Segmentation Medical Image Segmentation +4

SnakeGAN: A Universal Vocoder Leveraging DDSP Prior Knowledge and Periodic Inductive Bias

no code implementations14 Sep 2023 Sipan Li, Songxiang Liu, Luwen Zhang, Xiang Li, Yanyao Bian, Chao Weng, Zhiyong Wu, Helen Meng

However, it is still challenging to train a universal vocoder which can generalize well to out-of-domain (OOD) scenarios, such as unseen speaking styles, non-speech vocalization, singing, and musical pieces.

Audio Synthesis Generative Adversarial Network +1

Quantifying and Attributing the Hallucination of Large Language Models via Association Analysis

no code implementations11 Sep 2023 Li Du, Yequan Wang, Xingrun Xing, Yiqun Ya, Xiang Li, Xin Jiang, Xuezhi Fang

Although demonstrating superb performance on various NLP tasks, large language models (LLMs) still suffer from the hallucination problem, which threatens the reliability of LLMs.

Hallucination Instruction Following +2

FLM-101B: An Open LLM and How to Train It with $100K Budget

no code implementations7 Sep 2023 Xiang Li, Yiqun Yao, Xin Jiang, Xuezhi Fang, Xuying Meng, Siqi Fan, Peng Han, Jing Li, Li Du, Bowen Qin, Zheng Zhang, Aixin Sun, Yequan Wang

We demonstrate that a 101B-parameter LLM with 0. 31T tokens can be trained with a budget of 100K US dollars.

Memorization

Exchanging-based Multimodal Fusion with Transformer

1 code implementation5 Sep 2023 Renyu Zhu, Chengcheng Han, Yong Qian, Qiushi Sun, Xiang Li, Ming Gao, Xuezhi Cao, Yunsen Xian

To solve these issues, in this paper, we propose a novel exchanging-based multimodal fusion model MuSE for text-vision fusion based on Transformer.

Image Captioning Multimodal Sentiment Analysis +3

Graph Self-Contrast Representation Learning

no code implementations5 Sep 2023 Minjie Chen, Yao Cheng, Ye Wang, Xiang Li, Ming Gao

Further, Since the triplet loss only optimizes the relative distance between the anchor and its positive/negative samples, it is difficult to ensure the absolute distance between the anchor and positive sample.

Contrastive Learning Graph Representation Learning +1

RigNet++: Semantic Assisted Repetitive Image Guided Network for Depth Completion

no code implementations1 Sep 2023 Zhiqiang Yan, Xiang Li, Le Hui, Zhenyu Zhang, Jun Li, Jian Yang

To tackle these challenges, we explore a repetitive design in our image guided network to gradually and sufficiently recover depth values.

Depth Completion Depth Estimation +1

StratMed: Relevance Stratification between Biomedical Entities for Sparsity on Medication Recommendation

no code implementations31 Aug 2023 Xiang Li, Shunpan Liang, Yulei Hou, Tengfei Ma

After that, we design a pyramid-like stratification method based on relevance to strengthen the expressiveness of sparse data.

Listen to Minority: Encrypted Traffic Classification for Class Imbalance with Contrastive Pre-Training

no code implementations31 Aug 2023 Xiang Li, Juncheng Guo, Qige Song, Jiang Xie, Yafei Sang, Shuyuan Zhao, Yongzheng Zhang

Despite some existing learning-based ETC methods showing promising results, three-fold limitations still remain in real-world network environments, 1) label bias caused by traffic class imbalance, 2) traffic homogeneity caused by component sharing, and 3) training with reliance on sufficient labeled traffic.

Pseudo Label Traffic Classification

Mobile Foundation Model as Firmware

1 code implementation28 Aug 2023 Jinliang Yuan, Chen Yang, Dongqi Cai, Shihe Wang, Xin Yuan, Zeling Zhang, Xiang Li, Dingge Zhang, Hanzi Mei, Xianqing Jia, Shangguang Wang, Mengwei Xu

Concurrently, each app contributes a concise, offline fine-tuned "adapter" tailored to distinct downstream tasks.

FwdLLM: Efficient FedLLM using Forward Gradient

1 code implementation26 Aug 2023 Mengwei Xu, Dongqi Cai, Yaozong Wu, Xiang Li, Shangguang Wang

Federated Learning (FL), a method to preserve user data privacy, is often employed in fine-tuning LLMs to downstream mobile tasks, an approach known as FedLLM.

Federated Learning

Decoding Natural Images from EEG for Object Recognition

2 code implementations25 Aug 2023 Yonghao Song, Bingchuan Liu, Xiang Li, Nanlin Shi, Yijun Wang, Xiaorong Gao

This paper presents a self-supervised framework to demonstrate the feasibility of learning image representations from EEG signals, particularly for object recognition.

Contrastive Learning EEG +3

ADNet: Lane Shape Prediction via Anchor Decomposition

2 code implementations ICCV 2023 Lingyu Xiao, Xiang Li, Sen yang, Wankou Yang

In this paper, we revisit the limitations of anchor-based lane detection methods, which have predominantly focused on fixed anchors that stem from the edges of the image, disregarding their versatility and quality.

Lane Detection

Relation-Oriented: Toward Causal Knowledge-Aligned AGI

no code implementations31 Jul 2023 Jia Li, Xiang Li

Observation-Oriented paradigm currently dominates relationship learning models, including AI-based ones, which inherently do not account for relationships with temporally nonlinear effects.

Relation Representation Learning

UPFL: Unsupervised Personalized Federated Learning towards New Clients

no code implementations29 Jul 2023 Tiandi Ye, Cen Chen, Yinggui Wang, Xiang Li, Ming Gao

To address this challenge, we extend the adaptive risk minimization technique into the unsupervised personalized federated learning setting and propose our method, FedTTA.

Knowledge Distillation Personalized Federated Learning

You Can Backdoor Personalized Federated Learning

1 code implementation29 Jul 2023 Tiandi Ye, Cen Chen, Yinggui Wang, Xiang Li, Ming Gao

The resistance of pFL methods with parameter decoupling is attributed to the heterogeneous classifiers between malicious clients and benign counterparts.

Backdoor Attack Meta-Learning +1

MUSE: Multi-View Contrastive Learning for Heterophilic Graphs

no code implementations29 Jul 2023 Mengyi Yuan, Minjie Chen, Xiang Li

Finally, an alternating training scheme is adopted to ensure that unsupervised node representation learning and information fusion controller can mutually reinforce each other.

Contrastive Learning Node Classification +2

RSGPT: A Remote Sensing Vision Language Model and Benchmark

1 code implementation28 Jul 2023 Yuan Hu, Jianlong Yuan, Congcong Wen, Xiaonan Lu, Xiang Li

This dataset consists of human-annotated captions and visual question-answer pairs, allowing for a comprehensive assessment of VLMs in the context of RS.

Image Captioning Language Modelling

Rethinking Voice-Face Correlation: A Geometry View

no code implementations26 Jul 2023 Xiang Li, Yandong Wen, Muqiao Yang, Jinglu Wang, Rita Singh, Bhiksha Raj

Previous works on voice-face matching and voice-guided face synthesis demonstrate strong correlations between voice and face, but mainly rely on coarse semantic cues such as gender, age, and emotion.

3D Face Reconstruction Face Generation

Creative Birds: Self-Supervised Single-View 3D Style Transfer

2 code implementations ICCV 2023 Renke Wang, Guimin Que, Shuo Chen, Xiang Li, Jun Li, Jian Yang

Our focus lies primarily on birds, a popular subject in 3D reconstruction, for which no existing single-view 3D transfer methods have been developed. The method we propose seeks to generate a 3D mesh shape and texture of a bird from two single-view images.

3D Reconstruction Style Transfer

CohortGPT: An Enhanced GPT for Participant Recruitment in Clinical Study

no code implementations21 Jul 2023 Zihan Guan, Zihao Wu, Zhengliang Liu, Dufan Wu, Hui Ren, Quanzheng Li, Xiang Li, Ninghao Liu

Participant recruitment based on unstructured medical texts such as clinical notes and radiology reports has been a challenging yet important task for the cohort establishment in clinical research.

Few-Shot Learning text-classification +1

Review of Large Vision Models and Visual Prompt Engineering

no code implementations3 Jul 2023 Jiaqi Wang, Zhengliang Liu, Lin Zhao, Zihao Wu, Chong Ma, Sigang Yu, Haixing Dai, Qiushi Yang, Yiheng Liu, Songyao Zhang, Enze Shi, Yi Pan, Tuo Zhang, Dajiang Zhu, Xiang Li, Xi Jiang, Bao Ge, Yixuan Yuan, Dinggang Shen, Tianming Liu, Shu Zhang

This review aims to summarize the methods employed in the computer vision domain for large vision models and visual prompt engineering, exploring the latest advancements in visual prompt engineering.

Prompt Engineering

Higher-order Graph Attention Network for Stock Selection with Joint Analysis

no code implementations27 Jun 2023 Yang Qiao, Yiping Xia, Xiang Li, Zheng Li, Yan Ge

H-GAT is able to capture higher-order structures and jointly incorporate factors of fundamental analysis with factors of technical analysis.

Graph Attention Relation +1

Privacy-Preserving Community Detection for Locally Distributed Multiple Networks

no code implementations27 Jun 2023 Xiao Guo, Xiang Li, Xiangyu Chang, Shujie Ma

To remove the bias incurred by RR and the squared network matrices, we develop a two-step bias-adjustment procedure.

Clustering Community Detection +2

Segment Anything Model (SAM) for Radiation Oncology

no code implementations20 Jun 2023 Lian Zhang, Zhengliang Liu, Lu Zhang, Zihao Wu, Xiaowei Yu, Jason Holmes, Hongying Feng, Haixing Dai, Xiang Li, Quanzheng Li, Dajiang Zhu, Tianming Liu, Wei Liu

Given that SAM, a model pre-trained purely on natural images, can handle the delineation of OARs from medical images with clinically acceptable accuracy, these results highlight SAM's robust generalization capabilities with consistent accuracy in automatic segmentation for radiotherapy.

Segmentation

CrossKD: Cross-Head Knowledge Distillation for Dense Object Detection

1 code implementation20 Jun 2023 Jiabao Wang, Yuming Chen, Zhaohui Zheng, Xiang Li, Ming-Ming Cheng, Qibin Hou

Such a distillation manner relieves the student's head from receiving contradictory supervision signals from the ground-truth annotations and the teacher's predictions, greatly improving the student's detection performance.

Dense Object Detection Knowledge Distillation +3

AD-AutoGPT: An Autonomous GPT for Alzheimer's Disease Infodemiology

no code implementations16 Jun 2023 Haixing Dai, Yiwei Li, Zhengliang Liu, Lin Zhao, Zihao Wu, Suhang Song, Ye Shen, Dajiang Zhu, Xiang Li, Sheng Li, Xiaobai Yao, Lu Shi, Quanzheng Li, Zhuo Chen, Donglan Zhang, Gengchen Mai, Tianming Liu

In this pioneering study, inspired by AutoGPT, the state-of-the-art open-source application based on the GPT-4 large language model, we develop a novel tool called AD-AutoGPT which can conduct data collection, processing, and analysis about complex health narratives of Alzheimer's Disease in an autonomous manner via users' textual prompts.

Language Modelling Large Language Model

Shapley Value on Probabilistic Classifiers

no code implementations12 Jun 2023 Xiang Li, Haocheng Xia, Jinfei Liu

Data valuation has become an increasingly significant discipline in data science due to the economic value of data.

Data Valuation

Network Robustness Learning via Graph Transformer

no code implementations12 Jun 2023 Yu Zhang, Jia Li, Jie Ding, Xiang Li

Learning and analysis of network robustness, including controllability robustness and connectivity robustness, is critical for various networked systems against attacks.

Boosting Language Models Reasoning with Chain-of-Knowledge Prompting

no code implementations10 Jun 2023 Jianing Wang, Qiushi Sun, Nuo Chen, Xiang Li, Ming Gao

To mitigate this brittleness, we propose a novel Chain-of-Knowledge (CoK) prompting, where we aim at eliciting LLMs to generate explicit pieces of knowledge evidence in the form of structure triple.

Arithmetic Reasoning

Artificial General Intelligence for Medical Imaging

no code implementations8 Jun 2023 Xiang Li, Lu Zhang, Zihao Wu, Zhengliang Liu, Lin Zhao, Yixuan Yuan, Jun Liu, Gang Li, Dajiang Zhu, Pingkun Yan, Quanzheng Li, Wei Liu, Tianming Liu, Dinggang Shen

In this review, we explore the potential applications of Artificial General Intelligence (AGI) models in healthcare, focusing on foundational Large Language Models (LLMs), Large Vision Models, and Large Multimodal Models.

Variable Radiance Field for Real-Life Category-Specifc Reconstruction from Single Image

no code implementations8 Jun 2023 Kun Wang, Zhiqiang Yan, Zhenyu Zhang, Xiang Li, Jun Li, Jian Yang

Our key contributions are: (1) We parameterize the geometry and appearance of the object using a multi-scale global feature extractor, which avoids frequent point-wise feature retrieval and camera dependency.

Contrastive Learning Object +1

Fine-Grained Visual Prompting

1 code implementation NeurIPS 2023 Lingfeng Yang, Yueze Wang, Xiang Li, Xinlong Wang, Jian Yang

Previous works have suggested that incorporating visual prompts, such as colorful boxes or circles, can improve the ability of models to recognize objects of interest.

Visual Prompting

Modeling Dual Period-Varying Preferences for Takeaway Recommendation

1 code implementation7 Jun 2023 Yuting Zhang, Yiqing Wu, Ran Le, Yongchun Zhu, Fuzhen Zhuang, Ruidong Han, Xiang Li, Wei Lin, Zhulin An, Yongjun Xu

Different from traditional recommendation, takeaway recommendation faces two main challenges: (1) Dual Interaction-Aware Preference Modeling.

Recommendation Systems

Exploring Better Text Image Translation with Multimodal Codebook

1 code implementation27 May 2023 Zhibin Lan, Jiawei Yu, Xiang Li, Wen Zhang, Jian Luan, Bin Wang, Degen Huang, Jinsong Su

Text image translation (TIT) aims to translate the source texts embedded in the image to target translations, which has a wide range of applications and thus has important research value.

Machine Translation Optical Character Recognition +2

TransCoder: Towards Unified Transferable Code Representation Learning Inspired by Human Skills

no code implementations23 May 2023 Qiushi Sun, Nuo Chen, Jianing Wang, Xiang Li, Ming Gao

To tackle the issue, in this paper, we present TransCoder, a unified Transferable fine-tuning strategy for Code representation learning.

Clone Detection Code Summarization +2

Is Synthetic Data From Diffusion Models Ready for Knowledge Distillation?

1 code implementation22 May 2023 Zheng Li, YuXuan Li, Penghai Zhao, RenJie Song, Xiang Li, Jian Yang

Diffusion models have recently achieved astonishing performance in generating high-fidelity photo-realistic images.

Data-free Knowledge Distillation

S$^3$HQA: A Three-Stage Approach for Multi-hop Text-Table Hybrid Question Answering

1 code implementation19 May 2023 Fangyu Lei, Xiang Li, Yifan Wei, Shizhu He, Yiming Huang, Jun Zhao, Kang Liu

In this paper, we propose a three-stage TextTableQA framework S3HQA, which comprises of retriever, selector, and reasoner.

Question Answering Reading Comprehension

SPP-CNN: An Efficient Framework for Network Robustness Prediction

no code implementations13 May 2023 Chengpei Wu, Yang Lou, Lin Wang, Junli Li, Xiang Li, Guanrong Chen

This paper addresses the robustness of a network to sustain its connectivity and controllability against malicious attacks.

Dual Intent Enhanced Graph Neural Network for Session-based New Item Recommendation

1 code implementation10 May 2023 Di Jin, Luzhi Wang, Yizhen Zheng, Guojie Song, Fei Jiang, Xiang Li, Wei Lin, Shirui Pan

We design a dual-intent network to learn user intent from an attention mechanism and the distribution of historical data respectively, which can simulate users' decision-making process in interacting with a new item.

Decision Making Session-Based Recommendations +1

Vision-Language Models in Remote Sensing: Current Progress and Future Trends

2 code implementations9 May 2023 Congcong Wen, Yuan Hu, Xiang Li, Zhenghang Yuan, Xiao Xiang Zhu

This makes them better suited for tasks that require both visual and textual understanding, such as image captioning, text-based image retrieval, and visual question answering.

Image Captioning Image Generation +8

ChatGraph: Interpretable Text Classification by Converting ChatGPT Knowledge to Graphs

1 code implementation3 May 2023 Yucheng Shi, Hehuan Ma, Wenliang Zhong, Qiaoyu Tan, Gengchen Mai, Xiang Li, Tianming Liu, Junzhou Huang

To tackle these limitations, we propose a novel framework that leverages the power of ChatGPT for specific tasks, such as text classification, while improving its interpretability.

Decision Making Language Modelling +3

FreeLM: Fine-Tuning-Free Language Model

no code implementations2 May 2023 Xiang Li, Xin Jiang, Xuying Meng, Aixin Sun, Yequan Wang

FreeLM outperforms large models e. g., GPT-3 and InstructGPT, on a range of language understanding tasks in experiments.

Language Modelling

Instruction-ViT: Multi-Modal Prompts for Instruction Learning in ViT

no code implementations29 Apr 2023 Zhenxiang Xiao, Yuzhong Chen, Lu Zhang, Junjie Yao, Zihao Wu, Xiaowei Yu, Yi Pan, Lin Zhao, Chong Ma, Xinyu Liu, Wei Liu, Xiang Li, Yixuan Yuan, Dinggang Shen, Dajiang Zhu, Tianming Liu, Xi Jiang

Prompts have been proven to play a crucial role in large language models, and in recent years, vision models have also been using prompts to improve scalability for multiple downstream tasks.

Image Classification

Prompt Engineering for Healthcare: Methodologies and Applications

no code implementations28 Apr 2023 Jiaqi Wang, Enze Shi, Sigang Yu, Zihao Wu, Chong Ma, Haixing Dai, Qiushi Yang, Yanqing Kang, Jinru Wu, Huawen Hu, Chenxi Yue, Haiyang Zhang, Yiheng Liu, Yi Pan, Zhengliang Liu, Lichao Sun, Xiang Li, Bao Ge, Xi Jiang, Dajiang Zhu, Yixuan Yuan, Dinggang Shen, Tianming Liu, Shu Zhang

Prompt engineering is a critical technique in the field of natural language processing that involves designing and optimizing the prompts used to input information into models, aiming to enhance their performance on specific tasks.

Machine Translation Prompt Engineering +3

Asymptotic Behaviors and Phase Transitions in Projected Stochastic Approximation: A Jump Diffusion Approach

no code implementations25 Apr 2023 Jiadong Liang, Yuze Han, Xiang Li, Zhihua Zhang

Additionally, we propose the Debiased LPSA (DLPSA) as a practical application of our jump diffusion approximation result.

Differentiate ChatGPT-generated and Human-written Medical Texts

no code implementations23 Apr 2023 Wenxiong Liao, Zhengliang Liu, Haixing Dai, Shaochen Xu, Zihao Wu, Yiyang Zhang, Xiaoke Huang, Dajiang Zhu, Hongmin Cai, Tianming Liu, Xiang Li

We focus on analyzing the differences between medical texts written by human experts and generated by ChatGPT, and designing machine learning workflows to effectively detect and differentiate medical texts generated by ChatGPT.

ChatABL: Abductive Learning via Natural Language Interaction with ChatGPT

no code implementations21 Apr 2023 Tianyang Zhong, Yaonai Wei, Li Yang, Zihao Wu, Zhengliang Liu, Xiaozheng Wei, Wenjun Li, Junjie Yao, Chong Ma, Xiang Li, Dajiang Zhu, Xi Jiang, Junwei Han, Dinggang Shen, Tianming Liu, Tuo Zhang

The proposed method uses the strengths of LLMs' understanding and logical reasoning to correct the incomplete logical facts for optimizing the performance of perceptual module, by summarizing and reorganizing reasoning rules represented in natural language format.

Decipherment Logical Reasoning

MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models

5 code implementations20 Apr 2023 Deyao Zhu, Jun Chen, Xiaoqian Shen, Xiang Li, Mohamed Elhoseiny

Our work, for the first time, uncovers that properly aligning the visual features with an advanced large language model can possess numerous advanced multi-modal abilities demonstrated by GPT-4, such as detailed image description generation and website creation from hand-drawn drafts.

Language Modelling Large Language Model +2

Exploring the Trade-Offs: Unified Large Language Models vs Local Fine-Tuned Models for Highly-Specific Radiology NLI Task

no code implementations18 Apr 2023 Zihao Wu, Lu Zhang, Chao Cao, Xiaowei Yu, Haixing Dai, Chong Ma, Zhengliang Liu, Lin Zhao, Gang Li, Wei Liu, Quanzheng Li, Dinggang Shen, Xiang Li, Dajiang Zhu, Tianming Liu

To this end, in this study, we evaluate the performance of ChatGPT/GPT-4 on a radiology NLI task and compare it to other models fine-tuned specifically on task-related data samples.

Specificity Task 2

ImpressionGPT: An Iterative Optimizing Framework for Radiology Report Summarization with ChatGPT

2 code implementations17 Apr 2023 Chong Ma, Zihao Wu, Jiaqi Wang, Shaochen Xu, Yaonai Wei, Zhengliang Liu, Xi Jiang, Lei Guo, Xiaoyan Cai, Shu Zhang, Tuo Zhang, Dajiang Zhu, Dinggang Shen, Tianming Liu, Xiang Li

The 'Impression' section of a radiology report is a critical basis for communication between radiologists and other physicians, and it is typically written by radiologists based on the 'Findings' section.

In-Context Learning

Video ChatCaptioner: Towards Enriched Spatiotemporal Descriptions

1 code implementation9 Apr 2023 Jun Chen, Deyao Zhu, Kilichbek Haydarov, Xiang Li, Mohamed Elhoseiny

Video captioning aims to convey dynamic scenes from videos using natural language, facilitating the understanding of spatiotemporal information within our environment.

Video Captioning

MoStGAN-V: Video Generation with Temporal Motion Styles

1 code implementation CVPR 2023 Xiaoqian Shen, Xiang Li, Mohamed Elhoseiny

Video generation remains a challenging task due to spatiotemporal complexity and the requirement of synthesizing diverse motions with temporal consistency.

Video Generation

Summary of ChatGPT-Related Research and Perspective Towards the Future of Large Language Models

no code implementations4 Apr 2023 Yiheng Liu, Tianle Han, Siyuan Ma, Jiayue Zhang, Yuanyuan Yang, Jiaming Tian, Hao He, Antong Li, Mengshen He, Zhengliang Liu, Zihao Wu, Lin Zhao, Dajiang Zhu, Xiang Li, Ning Qiang, Dingang Shen, Tianming Liu, Bao Ge

This paper presents a comprehensive survey of ChatGPT-related (GPT-3. 5 and GPT-4) research, state-of-the-art large language models (LLM) from the GPT series, and their prospective applications across diverse domains.

When Brain-inspired AI Meets AGI

no code implementations28 Mar 2023 Lin Zhao, Lu Zhang, Zihao Wu, Yuzhong Chen, Haixing Dai, Xiaowei Yu, Zhengliang Liu, Tuo Zhang, Xintao Hu, Xi Jiang, Xiang Li, Dajiang Zhu, Dinggang Shen, Tianming Liu

Artificial General Intelligence (AGI) has been a long-standing goal of humanity, with the aim of creating machines capable of performing any intellectual task that humans can do.

In-Context Learning

On de novo Bridging Paired-end RNA-seq Data

1 code implementation27 Mar 2023 Xiang Li, Mingfu Shao

Methods have been proposed to bridge paired-end reads in the presence of reference genome (called reference-based bridging), but the algorithms are far away from scaling for de novo bridging as the underlying compacted de Bruijn graph(cdBG) used in the latter task often contains millions of vertices and edges.

A Survey of Historical Learning: Learning Models with Learning History

1 code implementation23 Mar 2023 Xiang Li, Ge Wu, Lingfeng Yang, Wenhai Wang, RenJie Song, Jian Yang

The various types of elements, deposited in the training history, are a large amount of wealth for improving learning deep models.

Ensemble Learning

DeID-GPT: Zero-shot Medical Text De-Identification by GPT-4

1 code implementation20 Mar 2023 Zhengliang Liu, Yue Huang, Xiaowei Yu, Lu Zhang, Zihao Wu, Chao Cao, Haixing Dai, Lin Zhao, Yiwei Li, Peng Shu, Fang Zeng, Lichao Sun, Wei Liu, Dinggang Shen, Quanzheng Li, Tianming Liu, Dajiang Zhu, Xiang Li

The digitization of healthcare has facilitated the sharing and re-using of medical data but has also raised concerns about confidentiality and privacy.

Benchmarking De-identification +4

Large Selective Kernel Network for Remote Sensing Object Detection

1 code implementation ICCV 2023 YuXuan Li, Qibin Hou, Zhaohui Zheng, Ming-Ming Cheng, Jian Yang, Xiang Li

To the best of our knowledge, this is the first time that large and selective kernel mechanisms have been explored in the field of remote sensing object detection.

Object object-detection +3

Digital staining in optical microscopy using deep learning -- a review

no code implementations14 Mar 2023 Lucas Kreiss, Shaowei Jiang, Xiang Li, Shiqi Xu, Kevin C. Zhou, Alexander Mühlberg, Kyung Chul Lee, Kanghyun Kim, Amey Chaware, Michael Ando, Laura Barisoni, Seung Ah Lee, Guoan Zheng, Kyle Lafata, Oliver Friedrich, Roarke Horstmeyer

Until recently, conventional biochemical staining had the undisputed status as well-established benchmark for most biomedical problems related to clinical diagnostics, fundamental research and biotechnology.

Specificity

Sufficient Control of Complex Networks

no code implementations10 Mar 2023 Xiang Li, Guoqi Li, Leitao Gao, Beibei Li, Gaoxi Xiao

In this paper, we propose to study on sufficient control of complex networks which is to control a sufficiently large portion of the network, where only the quantity of controllable nodes matters.

Variance-aware robust reinforcement learning with linear function approximation under heavy-tailed rewards

no code implementations9 Mar 2023 Xiang Li, Qiang Sun

Building upon AdaOFUL, we propose VARA for linear MDPs, which achieves a tighter variance-aware regret bound of $\widetilde{O}(d\sqrt{HG^*K})$.

Decision Making regression +2

Non-aligned supervision for Real Image Dehazing

no code implementations8 Mar 2023 Junkai Fan, Fei Guo, Jianjun Qian, Xiang Li, Jun Li, Jian Yang

In particular, we explore a non-alignment scenario that a clear reference image, unaligned with the input hazy image, is utilized to supervise the dehazing network.

Image Dehazing

Rethinking the Reasonability of the Test Set for Simultaneous Machine Translation

1 code implementation2 Mar 2023 Mengge Liu, Wen Zhang, Xiang Li, Jian Luan, Bin Wang, Yuhang Guo, Shuoying Chen

Simultaneous machine translation (SimulMT) models start translation before the end of the source sentence, making the translation monotonically aligned with the source sentence.

Machine Translation Sentence +1

HopFIR: Hop-wise GraphFormer with Intragroup Joint Refinement for 3D Human Pose Estimation

no code implementations ICCV 2023 Kai Zhai, Qiang Nie, Bo Ouyang, Xiang Li, Shanlin Yang

The HGF module groups the joints by k-hop neighbors and applies a hopwise transformer-like attention mechanism to these groups to discover latent joint synergies.

3D Human Pose Estimation

Pushing One Pair of Labels Apart Each Time in Multi-Label Learning: From Single Positive to Full Labels

no code implementations28 Feb 2023 Xiang Li, Xinrui Wang, Songcan Chen

In Multi-Label Learning (MLL), it is extremely challenging to accurately annotate every appearing object due to expensive costs and limited knowledge.

Multi-Label Learning

GradMA: A Gradient-Memory-based Accelerated Federated Learning with Alleviated Catastrophic Forgetting

1 code implementation CVPR 2023 Kangyang Luo, Xiang Li, Yunshi Lan, Ming Gao

Federated Learning (FL) has emerged as a de facto machine learning area and received rapid increasing research interests from the community.

Continual Learning Federated Learning +1

Statistical Analysis of Karcher Means for Random Restricted PSD Matrices

no code implementations24 Feb 2023 Hengchao Chen, Xiang Li, Qiang Sun

Non-asymptotic statistical analysis is often missing for modern geometry-aware machine learning algorithms due to the possibly intricate non-linear manifold structure.

Online Statistical Inference for Nonlinear Stochastic Approximation with Markovian Data

no code implementations15 Feb 2023 Xiang Li, Jiadong Liang, Zhihua Zhang

We study the statistical inference of nonlinear stochastic approximation algorithms utilizing a single trajectory of Markovian data.

Q-Learning valid

Meta-Learning Triplet Network with Adaptive Margins for Few-Shot Named Entity Recognition

1 code implementation14 Feb 2023 Chengcheng Han, Renyu Zhu, Jun Kuang, FengJiao Chen, Xiang Li, Ming Gao, Xuezhi Cao, Wei Wu

We design an improved triplet network to map samples and prototype vectors into a low-dimensional space that is easier to be classified and propose an adaptive margin for each entity type.

few-shot-ner Few-shot NER +5

Meta-Learning Siamese Network for Few-Shot Text Classification

1 code implementation5 Feb 2023 Chengcheng Han, Yuhe Wang, Yingnan Fu, Xiang Li, Minghui Qiu, Ming Gao, Aoying Zhou

Few-shot learning has been used to tackle the problem of label scarcity in text classification, of which meta-learning based methods have shown to be effective, such as the prototypical networks (PROTO).

Descriptive Few-Shot Learning +2

Structure Flow-Guided Network for Real Depth Super-Resolution

no code implementations31 Jan 2023 Jiayi Yuan, Haobo Jiang, Xiang Li, Jianjun Qian, Jun Li, Jian Yang

Specifically, our framework consists of a cross-modality flow-guided upsampling network (CFUNet) and a flow-enhanced pyramid edge attention network (PEANet).

Depth Estimation Depth Prediction +1

Recurrent Structure Attention Guidance for Depth Super-Resolution

no code implementations31 Jan 2023 Jiayi Yuan, Haobo Jiang, Xiang Li, Jianjun Qian, Jun Li, Jian Yang

Second, instead of the coarse concatenation guidance, we propose a recurrent structure attention block, which iteratively utilizes the latest depth estimation and the image features to jointly select clear patterns and boundaries, aiming at providing refined guidance for accurate depth recovery.

Depth Estimation Super-Resolution

SeeGera: Self-supervised Semi-implicit Graph Variational Auto-encoders with Masking

no code implementations29 Jan 2023 Xiang Li, Tiandi Ye, Caihua Shan, Dongsheng Li, Ming Gao

In this paper, to comprehensively enhance the performance of generative graph SSL against other GCL models on both unsupervised and supervised learning tasks, we propose the SeeGera model, which is based on the family of self-supervised variational graph auto-encoder (VGAE).

Contrastive Learning Self-Supervised Learning +1

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