Search Results for author: Xing Li

Found 30 papers, 9 papers with code

HiCat: A Semi-Supervised Approach for Cell Type Annotation

no code implementations25 Nov 2024 Chang Bi, Kailun Bai, Xing Li, Xuekui Zhang

This hybrid approach incorporates both reference and query genomic data for feature engineering, enhancing the embedding learning process, increasing the effective sample size for unsupervised techniques, and improving the transferability of the supervised model trained on reference data when applied to query datasets.

Dimensionality Reduction Feature Engineering

Constructive RNNs: An Error-Recurrence Perspective on Time-Variant Zero Finding Problem Solving Under Uncertainty

no code implementations12 Nov 2024 Mingxuan Sun, Xing Li, Han Wang

When facing time-variant problems in analog computing, the desirable RNN design requires finite-time convergence and robustness with respect to various types of uncertainties, due to the time-variant nature and difficulties in implementation.

SeaDAG: Semi-autoregressive Diffusion for Conditional Directed Acyclic Graph Generation

no code implementations21 Oct 2024 Xinyi Zhou, Xing Li, Yingzhao Lian, Yiwen Wang, Lei Chen, Mingxuan Yuan, Jianye Hao, Guangyong Chen, Pheng Ann Heng

We explicitly train the model to learn graph conditioning with a condition loss, which enhances the diffusion model's capacity to generate graphs that are both realistic and aligned with specified properties.

Decoder Denoising +1

Logic Synthesis Optimization with Predictive Self-Supervision via Causal Transformers

no code implementations16 Sep 2024 Raika Karimi, Faezeh Faez, Yingxue Zhang, Xing Li, Lei Chen, Mingxuan Yuan, Mahdi Biparva

Contemporary hardware design benefits from the abstraction provided by high-level logic gates, streamlining the implementation of logic circuits.

Reinforcement Learning (RL)

KAN-HyperpointNet for Point Cloud Sequence-Based 3D Human Action Recognition

no code implementations14 Sep 2024 Zhaoyu Chen, Xing Li, Qian Huang, Qiang Geng, Tianjin Yang, Shihao Han

In addition, we present a D-Hyperpoint KANsMixer module, which is recursively applied to nested groupings of D-Hyperpoints to learn the action discrimination information and creatively integrates Kolmogorov-Arnold Networks (KAN) to enhance spatio-temporal interaction within D-Hyperpoints.

3D Action Recognition Kolmogorov-Arnold Networks

MTLSO: A Multi-Task Learning Approach for Logic Synthesis Optimization

no code implementations9 Sep 2024 Faezeh Faez, Raika Karimi, Yingxue Zhang, Xing Li, Lei Chen, Mingxuan Yuan, Mahdi Biparva

On the other hand, we employ a hierarchical graph representation learning strategy to improve the model's capacity for learning expressive graph-level representations of large AIGs, surpassing traditional plain GNNs.

Graph Classification Graph Representation Learning +1

RTLRewriter: Methodologies for Large Models aided RTL Code Optimization

1 code implementation4 Sep 2024 Xufeng Yao, Yiwen Wang, Xing Li, Yingzhao Lian, Ran Chen, Lei Chen, Mingxuan Yuan, Hong Xu, Bei Yu

Our comparative analysis with established compilers such as Yosys and E-graph demonstrates significant improvements, highlighting the benefits of integrating large models into the early stages of circuit design.

Benchmarking

Logic Synthesis with Generative Deep Neural Networks

no code implementations7 Jun 2024 Xihan Li, Xing Li, Lei Chen, Xing Zhang, Mingxuan Yuan, Jun Wang

While deep learning has achieved significant success in various domains, its application to logic circuit design has been limited due to complex constraints and strict feasibility requirement.

Circuit Transformer: A Transformer That Preserves Logical Equivalence

no code implementations14 Mar 2024 Xihan Li, Xing Li, Lei Chen, Xing Zhang, Mingxuan Yuan, Jun Wang

In this study, we introduce a generative neural model, the "Circuit Transformer", which eliminates such wrong predictions and produces logic circuits strictly equivalent to given Boolean functions.

Hallucination

StreamVC: Real-Time Low-Latency Voice Conversion

no code implementations5 Jan 2024 Yang Yang, Yury Kartynnik, Yunpeng Li, Jiuqiang Tang, Xing Li, George Sung, Matthias Grundmann

We present StreamVC, a streaming voice conversion solution that preserves the content and prosody of any source speech while matching the voice timbre from any target speech.

Speech Synthesis Voice Conversion

A Circuit Domain Generalization Framework for Efficient Logic Synthesis in Chip Design

1 code implementation22 Aug 2023 Zhihai Wang, Lei Chen, Jie Wang, Xing Li, Yinqi Bai, Xijun Li, Mingxuan Yuan, Jianye Hao, Yongdong Zhang, Feng Wu

In particular, we notice that the runtime of the Resub and Mfs2 operators often dominates the overall runtime of LS optimization processes.

Domain Generalization

MataDoc: Margin and Text Aware Document Dewarping for Arbitrary Boundary

no code implementations24 Jul 2023 Beiya Dai, Xing Li, Qunyi Xie, Yulin Li, Xiameng Qin, Chengquan Zhang, Kun Yao, Junyu Han

To produce a comprehensive evaluation of MataDoc, we propose a novel benchmark ArbDoc, mainly consisting of document images with arbitrary boundaries in four typical scenarios.

document understanding Optical Character Recognition (OCR)

GAT-COBO: Cost-Sensitive Graph Neural Network for Telecom Fraud Detection

1 code implementation29 Mar 2023 Xinxin Hu, Haotian Chen, Junjie Zhang, Hongchang Chen, Shuxin Liu, Xing Li, Yahui Wang, xiangyang xue

Extensive experiments on two real-world telecom fraud detection datasets demonstrate that our proposed method is effective for the graph imbalance problem, outperforming the state-of-the-art GNNs and GNN-based fraud detectors.

Anomaly Detection Fraud Detection +3

Cost Sensitive GNN-based Imbalanced Learning for Mobile Social Network Fraud Detection

1 code implementation28 Mar 2023 Xinxin Hu, Haotian Chen, Hongchang Chen, Shuxin Liu, Xing Li, Shibo Zhang, Yahui Wang, xiangyang xue

But the imbalance problem in the aforementioned data, which could severely hinder the effectiveness of fraud detectors based on graph neural networks(GNN), has hardly been addressed in previous work.

Fraud Detection Graph Neural Network

Masked Representation Learning for Domain Generalized Stereo Matching

no code implementations CVPR 2023 Zhibo Rao, Bangshu Xiong, Mingyi He, Yuchao Dai, Renjie He, Zhelun Shen, Xing Li

Experimental results on multi-datasets show that: (1) our method can be easily plugged into the current various stereo matching models to improve generalization performance; (2) our method can reduce the significant volatility of generalization performance among different training epochs; (3) we find that the current methods prefer to choose the best results among different training epochs as generalization performance, but it is impossible to select the best performance by ground truth in practice.

Decoder Image Reconstruction +3

Augmentation for Learning From Demonstration with Environmental Constraints

no code implementations13 Oct 2022 Xing Li, Manuel Baum, Oliver Brock

We introduce a Learning from Demonstration (LfD) approach for contact-rich manipulation tasks with articulated mechanisms.

Parameter Convex Neural Networks

no code implementations11 Jun 2022 Jingcheng Zhou, Wei Wei, Xing Li, Bowen Pang, Zhiming Zheng

Deep learning utilizing deep neural networks (DNNs) has achieved a lot of success recently in many important areas such as computer vision, natural language processing, and recommendation systems.

Graph Attention Recommendation Systems

Real-time 3D human action recognition based on Hyperpoint sequence

1 code implementation16 Nov 2021 Xing Li, Qian Huang, Zhijian Wang, Zhenjie Hou, Tianjin Yang, Zhuang Miao

Instead of capturing spatio-temporal local structures, SequentialPointNet encodes the temporal evolution of static appearances to recognize human actions.

3D Action Recognition

Video Text Tracking With a Spatio-Temporal Complementary Model

1 code implementation9 Nov 2021 Yuzhe Gao, Xing Li, Jiajian Zhang, Yu Zhou, Dian Jin, Jing Wang, Shenggao Zhu, Xiang Bai

We leverage a Siamese ComplementaryModule to fully exploit the continuity characteristic of the textinstances in the temporal dimension, which effectively alleviatesthe missed detection of the text instances, and hence ensuresthe completeness of each text trajectory.

text similarity

Human Action Recognition Based on Multi-scale Feature Maps from Depth Video Sequences

no code implementations19 Jan 2021 Chang Li, Qian Huang, Xing Li, Qianhan Wu

We employ depth motion images (DMI) as the templates to generate the multi-scale static representation of actions.

Action Classification Action Recognition +1

Representation Learning of Reconstructed Graphs Using Random Walk Graph Convolutional Network

no code implementations2 Jan 2021 Xing Li, Wei Wei, Xiangnan Feng, Zhiming Zheng

Graphs are often used to organize data because of their simple topological structure, and therefore play a key role in machine learning.

Graph Neural Network Graph Representation Learning +2

Representation Learning of Graphs Using Graph Convolutional Multilayer Networks Based on Motifs

no code implementations31 Jul 2020 Xing Li, Wei Wei, Xiangnan Feng, Xue Liu, Zhiming Zheng

The graph structure is a commonly used data storage mode, and it turns out that the low-dimensional embedded representation of nodes in the graph is extremely useful in various typical tasks, such as node classification, link prediction , etc.

Clustering Graph Neural Network +3

Computer-aided implant design for the restoration of cranial defects

no code implementations23 Jun 2017 Xiaojun Chen, Lu Xu, Xing Li, Jan Egger

Patient-specific cranial implants are important and necessary in the surgery of cranial defect restoration.

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