Search Results for author: Min Li

Found 61 papers, 19 papers with code

DeepGate3: Towards Scalable Circuit Representation Learning

no code implementations15 Jul 2024 Zhengyuan Shi, Ziyang Zheng, Sadaf Khan, Jianyuan Zhong, Min Li, Qiang Xu

Circuit representation learning has shown promising results in advancing the field of Electronic Design Automation (EDA).

Representation Learning

GraphMamba: An Efficient Graph Structure Learning Vision Mamba for Hyperspectral Image Classification

no code implementations11 Jul 2024 Aitao Yang, Min Li, Yao Ding, Leyuan Fang, Yaoming Cai, Yujie He

Efficient extraction of spectral sequences and geospatial information has always been a hot topic in hyperspectral image classification.

Computational Efficiency Graph structure learning +1

AutoCAP: Towards Automatic Cross-lingual Alignment Planning for Zero-shot Chain-of-Thought

1 code implementation20 Jun 2024 Yongheng Zhang, Qiguang Chen, Min Li, Wanxiang Che, Libo Qin

Cross-lingual chain-of-thought can effectively complete reasoning tasks across languages, which gains increasing attention.

IR2QSM: Quantitative Susceptibility Mapping via Deep Neural Networks with Iterative Reverse Concatenations and Recurrent Modules

no code implementations18 Jun 2024 Min Li, Chen Chen, Zhuang Xiong, Ying Liu, Pengfei Rong, Shanshan Shan, Feng Liu, Hongfu Sun, Yang Gao

Quantitative susceptibility mapping (QSM) is an MRI phase-based post-processing technique to extract the distribution of tissue susceptibilities, demonstrating significant potential in studying neurological diseases.

CorrMAE: Pre-training Correspondence Transformers with Masked Autoencoder

no code implementations9 Jun 2024 Tangfei Liao, Xiaoqin Zhang, Guobao Xiao, Min Li, Tao Wang, Mang Ye

To tackle these challenges, we propose a pre-training method to acquire a generic inliers-consistent representation by reconstructing masked correspondences, providing a strong initial representation for downstream tasks.

Representation Learning

Leveraging Visual Tokens for Extended Text Contexts in Multi-Modal Learning

1 code implementation4 Jun 2024 Alex Jinpeng Wang, Linjie Li, Yiqi Lin, Min Li, Lijuan Wang, Mike Zheng Shou

Training models with longer in-context lengths is a significant challenge for multimodal model due to substantial GPU memory and computational costs.

document understanding Retrieval

Large Language Models Meet NLP: A Survey

1 code implementation21 May 2024 Libo Qin, Qiguang Chen, Xiachong Feng, Yang Wu, Yongheng Zhang, Yinghui Li, Min Li, Wanxiang Che, Philip S. Yu

While large language models (LLMs) like ChatGPT have shown impressive capabilities in Natural Language Processing (NLP) tasks, a systematic investigation of their potential in this field remains largely unexplored.

Multilingual Large Language Model: A Survey of Resources, Taxonomy and Frontiers

no code implementations7 Apr 2024 Libo Qin, Qiguang Chen, YuHang Zhou, Zhi Chen, Yinghui Li, Lizi Liao, Min Li, Wanxiang Che, Philip S. Yu

To this end, in this paper, we present a thorough review and provide a unified perspective to summarize the recent progress as well as emerging trends in multilingual large language models (MLLMs) literature.

Language Modelling Large Language Model

Localization of Dummy Data Injection Attacks in Power Systems Considering Incomplete Topological Information: A Spatio-Temporal Graph Wavelet Convolutional Neural Network Approach

no code implementations27 Jan 2024 Zhaoyang Qu, Yunchang Dong, Yang Li, Siqi Song, Tao Jiang, Min Li, Qiming Wang, Lei Wang, Xiaoyong Bo, Jiye Zang, Qi Xu

Unfortunately, this approach tends to overlook the inherent topological correlations within the non-Euclidean spatial attributes of power grid data, consequently leading to diminished accuracy in attack localization.

Relative Pose for Nonrigid Multi-Perspective Cameras: The Static Case

no code implementations17 Jan 2024 Min Li, Jiaqi Yang, Laurent Kneip

Multi-perspective cameras with potentially non-overlapping fields of view have become an important exteroceptive sensing modality in a number of applications such as intelligent vehicles, drones, and mixed reality headsets.

Mixed Reality

DTIAM: A unified framework for predicting drug-target interactions, binding affinities and activation/inhibition mechanisms

1 code implementation23 Dec 2023 Zhangli Lu, Chuqi Lei, Kaili Wang, Libo Qin, Jing Tang, Min Li

DTIAM, for the first time, provides a unified framework for accurate and robust prediction of drug-target interactions, binding affinities, and activation/inhibition mechanisms.

Drug Discovery

Increasing Coverage and Precision of Textual Information in Multilingual Knowledge Graphs

1 code implementation27 Nov 2023 Simone Conia, Min Li, Daniel Lee, Umar Farooq Minhas, Ihab Ilyas, Yunyao Li

Recent work in Natural Language Processing and Computer Vision has been using textual information -- e. g., entity names and descriptions -- available in knowledge graphs to ground neural models to high-quality structured data.

Entity Linking Machine Translation +1

End-to-end Task-oriented Dialogue: A Survey of Tasks, Methods, and Future Directions

no code implementations15 Nov 2023 Libo Qin, Wenbo Pan, Qiguang Chen, Lizi Liao, Zhou Yu, Yue Zhang, Wanxiang Che, Min Li

End-to-end task-oriented dialogue (EToD) can directly generate responses in an end-to-end fashion without modular training, which attracts escalating popularity.

Plug-and-Play Latent Feature Editing for Orientation-Adaptive Quantitative Susceptibility Mapping Neural Networks

1 code implementation14 Nov 2023 Yang Gao, Zhuang Xiong, Shanshan Shan, Yin Liu, Pengfei Rong, Min Li, Alan H Wilman, G. Bruce Pike, Feng Liu, Hongfu Sun

The proposed OA-LFE-empowered iQSM, which we refer to as iQSM+, is trained in a self-supervised manner on a specially-designed simulation brain dataset.

Joint Location Sensing and Channel Estimation for IRS-Aided mmWave ISAC Systems

no code implementations14 Nov 2023 Zijian Chen, Ming-Min Zhao, Min Li, Fan Xu, Qingqing Wu, Min-Jian Zhao

Based on the estimation results from the first phase, we formulate a Cram\'{e}r-Rao bound (CRB) minimization problem for optimizing IRS reflection coefficients, and through proper reformulations, a low-complexity manifold-based optimization algorithm is proposed to solve this problem.

Bayesian Inference POS

Fast algorithms for k-submodular maximization subject to a matroid constraint

no code implementations26 Jul 2023 Shuxian Niu, Qian Liu, Yang Zhou, Min Li

In this paper, we apply a Threshold-Decreasing Algorithm to maximize $k$-submodular functions under a matroid constraint, which reduces the query complexity of the algorithm compared to the greedy algorithm with little loss in approximation ratio.

INGB: Informed Nonlinear Granular Ball Oversampling Framework for Noisy Imbalanced Classification

1 code implementation3 Jul 2023 Min Li, Hao Zhou, Qun Liu, Yabin Shao, GuoYing Wang

It uses granular balls to simulate the spatial distribution characteristics of datasets, and informed entropy is utilized to further optimize the granular-ball space.

Anchor link prediction Diversity +1

Fast Segment Anything

1 code implementation21 Jun 2023 Xu Zhao, Wenchao Ding, Yongqi An, Yinglong Du, Tao Yu, Min Li, Ming Tang, Jinqiao Wang

In this paper, we propose a speed-up alternative method for this fundamental task with comparable performance.

Edge Detection Image Segmentation +6

DeepGate2: Functionality-Aware Circuit Representation Learning

1 code implementation25 May 2023 Zhengyuan Shi, Hongyang Pan, Sadaf Khan, Min Li, Yi Liu, Junhua Huang, Hui-Ling Zhen, Mingxuan Yuan, Zhufei Chu, Qiang Xu

Circuit representation learning aims to obtain neural representations of circuit elements and has emerged as a promising research direction that can be applied to various EDA and logic reasoning tasks.

Graph Neural Network Representation Learning

DeepSeq: Deep Sequential Circuit Learning

no code implementations27 Feb 2023 Sadaf Khan, Zhengyuan Shi, Min Li, Qiang Xu

Circuit representation learning is a promising research direction in the electronic design automation (EDA) field.

Graph Neural Network Representation Learning

TA-MoE: Topology-Aware Large Scale Mixture-of-Expert Training

1 code implementation20 Feb 2023 Chang Chen, Min Li, Zhihua Wu, dianhai yu, Chao Yang

In this paper, we propose TA-MoE, a topology-aware routing strategy for large-scale MoE trainging, from a model-system co-design perspective, which can dynamically adjust the MoE dispatch pattern according to the network topology.

Peak-First CTC: Reducing the Peak Latency of CTC Models by Applying Peak-First Regularization

no code implementations7 Nov 2022 Zhengkun Tian, Hongyu Xiang, Min Li, Feifei Lin, Ke Ding, Guanglu Wan

To reduce the peak latency, we propose a simple and novel method named peak-first regularization, which utilizes a frame-wise knowledge distillation function to force the probability distribution of the CTC model to shift left along the time axis instead of directly modifying the calculation process of CTC loss and gradients.

Knowledge Distillation

Coded Residual Transform for Generalizable Deep Metric Learning

no code implementations9 Oct 2022 Shichao Kan, Yixiong Liang, Min Li, Yigang Cen, Jianxin Wang, Zhihai He

To address this challenge, in this paper, we introduce a new method called coded residual transform (CRT) for deep metric learning to significantly improve its generalization capability.

Metric Learning

Fast geometric trim fitting using partial incremental sorting and accumulation

no code implementations5 Sep 2022 Min Li, Laurent Kneip

We apply our method to two distinct camera resectioning algorithms, and demonstrate highly efficient and reliable, geometric trim fitting.


SATformer: Transformer-Based UNSAT Core Learning

no code implementations2 Sep 2022 Zhengyuan Shi, Min Li, Yi Liu, Sadaf Khan, Junhua Huang, Hui-Ling Zhen, Mingxuan Yuan, Qiang Xu

This paper introduces SATformer, a novel Transformer-based approach for the Boolean Satisfiability (SAT) problem.

Graph Neural Network Multi-Task Learning

TripHLApan: predicting HLA molecules binding peptides based on triple coding matrix and transfer learning

no code implementations6 Aug 2022 Meng Wang, Chuqi Lei, Jianxin Wang, Yaohang Li, Min Li

In conclusion, TripHLApan is a powerful tool for predicting the binding of HLA-I and HLA-II molecular peptides for the synthesis of tumor vaccines.

Transfer Learning

PGMG: A Pharmacophore-Guided Deep Learning Approach for Bioactive Molecular Generation

1 code implementation2 Jul 2022 Huimin Zhu, Renyi Zhou, Jing Tang, Min Li

The rational design of novel molecules with desired bioactivity is a critical but challenging task in drug discovery, especially when treating a novel target family or understudied targets.

Diversity Drug Discovery

DeepTPI: Test Point Insertion with Deep Reinforcement Learning

1 code implementation7 Jun 2022 Zhengyuan Shi, Min Li, Sadaf Khan, Liuzheng Wang, Naixing Wang, Yu Huang, Qiang Xu

Unlike previous learning-based solutions that formulate the TPI task as a supervised-learning problem, we train a novel DRL agent, instantiated as the combination of a graph neural network (GNN) and a Deep Q-Learning network (DQN), to maximize the test coverage improvement.

Graph Neural Network Q-Learning +2

DeepSAT: An EDA-Driven Learning Framework for SAT

no code implementations27 May 2022 Min Li, Zhengyuan Shi, Qiuxia Lai, Sadaf Khan, Shaowei Cai, Qiang Xu

Based on this observation, we approximate the SAT solving procedure with a conditional generative model, leveraging a novel directed acyclic graph neural network (DAGNN) with two polarity prototypes for conditional SAT modeling.

Graph Neural Network

RAR-PINN algorithm for the data-driven vector-soliton solutions and parameter discovery of coupled nonlinear equations

no code implementations29 Apr 2022 Shu-Mei Qin, Min Li, Tao Xu, Shao-Qun Dong

This work aims to provide an effective deep learning framework to predict the vector-soliton solutions of the coupled nonlinear equations and their interactions.

Testability-Aware Low Power Controller Design with Evolutionary Learning

1 code implementation26 Nov 2021 Min Li, Zhengyuan Shi, Zezhong Wang, Weiwei Zhang, Yu Huang, Qiang Xu

The proposed GA-guided XORNets also allows reducing the number of control bits, and the total testing time decreases by 20. 78% on average and up to 47. 09% compared to the existing design without sacrificing test coverage.

DeepGate: Learning Neural Representations of Logic Gates

1 code implementation26 Nov 2021 Min Li, Sadaf Khan, Zhengyuan Shi, Naixing Wang, Yu Huang, Qiang Xu

We propose DeepGate, a novel representation learning solution that effectively embeds both logic function and structural information of a circuit as vectors on each gate.

Graph Neural Network Representation Learning

T-WaveNet: A Tree-Structured Wavelet Neural Network for Time Series Signal Analysis

no code implementations ICLR 2022 Minhao Liu, Ailing Zeng, Qiuxia Lai, Ruiyuan Gao, Min Li, Jing Qin, Qiang Xu

In this work, we propose a novel tree-structured wavelet neural network for time series signal analysis, namely T-WaveNet, by taking advantage of an inherent property of various types of signals, known as the dominant frequency range.

Activity Recognition Representation Learning +3

Rethinking the Misalignment Problem in Dense Object Detection

1 code implementation27 Aug 2021 Yang Yang, Min Li, Bo Meng, Junxing Ren, Degang Sun, Zihao Huang

On the basis of SALT and SDR loss, we propose SALT-Net, which explicitly exploits task-aligned point-set features for accurate detection results.

Dense Object Detection Object +2

A Pseudo Label-wise Attention Network for Automatic ICD Coding

no code implementations12 Jun 2021 Yifan Wu, Min Zeng, Ying Yu, Min Li

The label-wise attention mechanism is widely used in automatic ICD coding because it can assign weights to every word in full Electronic Medical Records (EMR) for different ICD codes.

Multi-Label Classification Pseudo Label

Hybrid gene selection approach using XGBoost and multi-objective genetic algorithm for cancer classification

no code implementations30 May 2021 Xiongshi Deng, Min Li, Shaobo Deng, Lei Wang

In the second stage, XGBoost-MOGA searches for an optimal gene subset based on the most relevant genes's group using a multi-objective optimization genetic algorithm.

feature selection

RFCBF: enhance the performance and stability of Fast Correlation-Based Filter

no code implementations30 May 2021 Xiongshi Deng, Min Li, Lei Wang, Qikang Wan

Feature selection is a preprocessing step which plays a crucial role in the domain of machine learning and data mining.

feature selection

TestRank: Bringing Order into Unlabeled Test Instances for Deep Learning Tasks

no code implementations NeurIPS 2021 Yu Li, Min Li, Qiuxia Lai, Yannan Liu, Qiang Xu

To be specific, we first build a similarity graph on test instances and training samples, and we conduct graph-based semi-supervised learning to extract contextual features.

Graph Neural Network Image Classification

AppealNet: An Efficient and Highly-Accurate Edge/Cloud Collaborative Architecture for DNN Inference

no code implementations10 May 2021 Min Li, Yu Li, Ye Tian, Li Jiang, Qiang Xu

This paper presents AppealNet, a novel edge/cloud collaborative architecture that runs deep learning (DL) tasks more efficiently than state-of-the-art solutions.

Image Classification

Objects as Extreme Points

no code implementations29 Apr 2021 Yang Yang, Min Li, Bo Meng, Zihao Huang, Junxing Ren, Degang Sun

We also propose a new metric to measure the similarity between two groups of extreme points, namely, Extreme Intersection over Union (EIoU), and incorporate this EIoU as a new regression loss.

Clustering Object +2

Skimming and Scanning for Untrimmed Video Action Recognition

no code implementations21 Apr 2021 Yunyan Hong, Ailing Zeng, Min Li, Cewu Lu, Li Jiang, Qiang Xu

Video action recognition (VAR) is a primary task of video understanding, and untrimmed videos are more common in real-life scenes.

Action Recognition Temporal Action Localization +1

BridgeDPI: A Novel Graph Neural Network for Predicting Drug-Protein Interactions

1 code implementation29 Jan 2021 Yifan Wu, Min Gao, Min Zeng, Feiyang Chen, Min Li, Jie Zhang

Therefore, we hope to develop a novel supervised learning method to learn the PPAs and DDAs effectively and thereby improve the prediction performance of the specific task of DPI.

Drug Discovery Graph Neural Network

KddRES: A Multi-level Knowledge-driven Dialogue Dataset for Restaurant Towards Customized Dialogue System

no code implementations17 Nov 2020 Hongru Wang, Min Li, Zimo Zhou, Gabriel Pui Cheong Fung, Kam-Fai Wong

In this paper, we publish a first Cantonese knowledge-driven Dialogue Dataset for REStaurant (KddRES) in Hong Kong, which grounds the information in multi-turn conversations to one specific restaurant.


a-Tucker: Input-Adaptive and Matricization-Free Tucker Decomposition for Dense Tensors on CPUs and GPUs

no code implementations20 Oct 2020 Min Li, Chuanfu Xiao, Chao Yang

A mode-wise flexible Tucker decomposition algorithm is proposed to enable the switch of different solvers for the factor matrices and core tensor, and a machine-learning adaptive solver selector is applied to automatically cope with the variations of both the input data and the hardware.

DeepDyve: Dynamic Verification for Deep Neural Networks

no code implementations21 Sep 2020 Yu Li, Min Li, Bo Luo, Ye Tian, Qiang Xu

The key to enabling such lightweight checking is that the smaller neural network only needs to produce approximate results for the initial task without sacrificing fault coverage much.

Autonomous Driving

Robust Adaptive Beam Tracking for Mobile Millimetre Wave Communications

no code implementations3 May 2020 Chunshan Liu, Min Li, Lou Zhao, Philip Whiting, Stephen V. Hanly, Iain B. Collings, MinJian Zhao

Millimetre wave (mmWave) beam tracking is a challenging task because tracking algorithms are required to provide consistent high accuracy with low probability of loss of track and minimal overhead.

Efficient Alternating Least Squares Algorithms for Low Multilinear Rank Approximation of Tensors

no code implementations6 Apr 2020 Chuanfu Xiao, Chao Yang, Min Li

In this paper, we propose a new class of truncated HOSVD algorithms based on alternating least squares (ALS) for efficiently computing the low multilinear rank approximation of tensors.

Multi-View Photometric Stereo: A Robust Solution and Benchmark Dataset for Spatially Varying Isotropic Materials

no code implementations18 Jan 2020 Min Li, Zhenglong Zhou, Zhe Wu, Boxin Shi, Changyu Diao, Ping Tan

From a single viewpoint, we use a set of photometric stereo images to identify surface points with the same distance to the camera.

UAV-Enabled Confidential Data Collection in Wireless Networks

no code implementations3 Jan 2020 Xiaobo Zhou, Shihao Yan, Min Li, Jun Li, Feng Shu

This work, for the first time, considers confidential data collection in the context of unmanned aerial vehicle (UAV) wireless networks, where the scheduled ground sensor node (SN) intends to transmit confidential information to the UAV without being intercepted by other unscheduled ground SNs.

On Configurable Defense against Adversarial Example Attacks

no code implementations6 Dec 2018 Bo Luo, Min Li, Yu Li, Qiang Xu

Machine learning systems based on deep neural networks (DNNs) have gained mainstream adoption in many applications.

DIMSIM: An Accurate Chinese Phonetic Similarity Algorithm Based on Learned High Dimensional Encoding

1 code implementation CONLL 2018 Min Li, Marina Danilevsky, Sara Noeman, Yunyao Li

Phonetic similarity algorithms identify words and phrases with similar pronunciation which are used in many natural language processing tasks.

Spelling Correction

Adaptive Primal-Dual Splitting Methods for Statistical Learning and Image Processing

no code implementations NeurIPS 2015 Tom Goldstein, Min Li, Xiaoming Yuan

The alternating direction method of multipliers (ADMM) is an important tool for solving complex optimization problems, but it involves minimization sub-steps that are often difficult to solve efficiently.

Identifying the Absorption Bump with Deep Learning

no code implementations17 Nov 2015 Min Li, Sudeep Gaddam, Xiaolin Li, Yinan Zhao, Jingzhe Ma, Jian Ge

In this paper, we apply Deep Learning techniques to detect the broad absorption bump.

Adaptive Primal-Dual Hybrid Gradient Methods for Saddle-Point Problems

1 code implementation2 May 2013 Tom Goldstein, Min Li, Xiaoming Yuan, Ernie Esser, Richard Baraniuk

The Primal-Dual hybrid gradient (PDHG) method is a powerful optimization scheme that breaks complex problems into simple sub-steps.

Numerical Analysis 65K15 G.1.6

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