Picture for Pingjie Wang

Pingjie Wang

Towards Omni-RAG: Comprehensive Retrieval-Augmented Generation for Large Language Models in Medical Applications

Add code
Jan 05, 2025
Figure 1 for Towards Omni-RAG: Comprehensive Retrieval-Augmented Generation for Large Language Models in Medical Applications
Figure 2 for Towards Omni-RAG: Comprehensive Retrieval-Augmented Generation for Large Language Models in Medical Applications
Figure 3 for Towards Omni-RAG: Comprehensive Retrieval-Augmented Generation for Large Language Models in Medical Applications
Figure 4 for Towards Omni-RAG: Comprehensive Retrieval-Augmented Generation for Large Language Models in Medical Applications
Viaarxiv icon

AuscultaBase: A Foundational Step Towards AI-Powered Body Sound Diagnostics

Add code
Nov 12, 2024
Figure 1 for AuscultaBase: A Foundational Step Towards AI-Powered Body Sound Diagnostics
Figure 2 for AuscultaBase: A Foundational Step Towards AI-Powered Body Sound Diagnostics
Figure 3 for AuscultaBase: A Foundational Step Towards AI-Powered Body Sound Diagnostics
Figure 4 for AuscultaBase: A Foundational Step Towards AI-Powered Body Sound Diagnostics
Viaarxiv icon

HSDreport: Heart Sound Diagnosis with Echocardiography Reports

Add code
Aug 16, 2024
Figure 1 for HSDreport: Heart Sound Diagnosis with Echocardiography Reports
Figure 2 for HSDreport: Heart Sound Diagnosis with Echocardiography Reports
Figure 3 for HSDreport: Heart Sound Diagnosis with Echocardiography Reports
Figure 4 for HSDreport: Heart Sound Diagnosis with Echocardiography Reports
Viaarxiv icon

Reconstruct the Pruned Model without Any Retraining

Add code
Jul 18, 2024
Viaarxiv icon

M2K-VDG: Model-Adaptive Multimodal Knowledge Anchor Enhanced Video-grounded Dialogue Generation

Add code
Feb 19, 2024
Figure 1 for M2K-VDG: Model-Adaptive Multimodal Knowledge Anchor Enhanced Video-grounded Dialogue Generation
Figure 2 for M2K-VDG: Model-Adaptive Multimodal Knowledge Anchor Enhanced Video-grounded Dialogue Generation
Figure 3 for M2K-VDG: Model-Adaptive Multimodal Knowledge Anchor Enhanced Video-grounded Dialogue Generation
Figure 4 for M2K-VDG: Model-Adaptive Multimodal Knowledge Anchor Enhanced Video-grounded Dialogue Generation
Viaarxiv icon