Picture for Zhiyuan Zhao

Zhiyuan Zhao

MinerU: An Open-Source Solution for Precise Document Content Extraction

Add code
Sep 27, 2024
Figure 1 for MinerU: An Open-Source Solution for Precise Document Content Extraction
Figure 2 for MinerU: An Open-Source Solution for Precise Document Content Extraction
Figure 3 for MinerU: An Open-Source Solution for Precise Document Content Extraction
Figure 4 for MinerU: An Open-Source Solution for Precise Document Content Extraction
Viaarxiv icon

Quantum-inspired Interpretable Deep Learning Architecture for Text Sentiment Analysis

Add code
Aug 15, 2024
Viaarxiv icon

StitchFusion: Weaving Any Visual Modalities to Enhance Multimodal Semantic Segmentation

Add code
Aug 02, 2024
Viaarxiv icon

TSI-Bench: Benchmarking Time Series Imputation

Add code
Jun 18, 2024
Viaarxiv icon

Time-Series Forecasting for Out-of-Distribution Generalization Using Invariant Learning

Add code
Jun 13, 2024
Viaarxiv icon

Time-MMD: A New Multi-Domain Multimodal Dataset for Time Series Analysis

Add code
Jun 12, 2024
Viaarxiv icon

Follow-Your-Pose v2: Multiple-Condition Guided Character Image Animation for Stable Pose Control

Add code
Jun 05, 2024
Viaarxiv icon

DSDL: Data Set Description Language for Bridging Modalities and Tasks in AI Data

Add code
May 28, 2024
Viaarxiv icon

U3M: Unbiased Multiscale Modal Fusion Model for Multimodal Semantic Segmentation

Add code
May 24, 2024
Viaarxiv icon

LSTPrompt: Large Language Models as Zero-Shot Time Series Forecasters by Long-Short-Term Prompting

Add code
Feb 25, 2024
Viaarxiv icon