Picture for Xiaoyuan Guo

Xiaoyuan Guo

IM-RAG: Multi-Round Retrieval-Augmented Generation Through Learning Inner Monologues

May 15, 2024
Viaarxiv icon

Higher Layers Need More LoRA Experts

Add code
Feb 13, 2024
Figure 1 for Higher Layers Need More LoRA Experts
Figure 2 for Higher Layers Need More LoRA Experts
Figure 3 for Higher Layers Need More LoRA Experts
Figure 4 for Higher Layers Need More LoRA Experts
Viaarxiv icon

Evaluation and Mitigation of Agnosia in Multimodal Large Language Models

Sep 07, 2023
Figure 1 for Evaluation and Mitigation of Agnosia in Multimodal Large Language Models
Figure 2 for Evaluation and Mitigation of Agnosia in Multimodal Large Language Models
Figure 3 for Evaluation and Mitigation of Agnosia in Multimodal Large Language Models
Figure 4 for Evaluation and Mitigation of Agnosia in Multimodal Large Language Models
Viaarxiv icon

Tackling Vision Language Tasks Through Learning Inner Monologues

Aug 19, 2023
Figure 1 for Tackling Vision Language Tasks Through Learning Inner Monologues
Figure 2 for Tackling Vision Language Tasks Through Learning Inner Monologues
Figure 3 for Tackling Vision Language Tasks Through Learning Inner Monologues
Figure 4 for Tackling Vision Language Tasks Through Learning Inner Monologues
Viaarxiv icon

LOWA: Localize Objects in the Wild with Attributes

May 31, 2023
Figure 1 for LOWA: Localize Objects in the Wild with Attributes
Figure 2 for LOWA: Localize Objects in the Wild with Attributes
Figure 3 for LOWA: Localize Objects in the Wild with Attributes
Figure 4 for LOWA: Localize Objects in the Wild with Attributes
Viaarxiv icon

Augmenting Vision Language Pretraining by Learning Codebook with Visual Semantics

Jul 31, 2022
Figure 1 for Augmenting Vision Language Pretraining by Learning Codebook with Visual Semantics
Figure 2 for Augmenting Vision Language Pretraining by Learning Codebook with Visual Semantics
Figure 3 for Augmenting Vision Language Pretraining by Learning Codebook with Visual Semantics
Figure 4 for Augmenting Vision Language Pretraining by Learning Codebook with Visual Semantics
Viaarxiv icon

OSCARS: An Outlier-Sensitive Content-Based Radiography Retrieval System

Add code
Apr 06, 2022
Figure 1 for OSCARS: An Outlier-Sensitive Content-Based Radiography Retrieval System
Figure 2 for OSCARS: An Outlier-Sensitive Content-Based Radiography Retrieval System
Figure 3 for OSCARS: An Outlier-Sensitive Content-Based Radiography Retrieval System
Figure 4 for OSCARS: An Outlier-Sensitive Content-Based Radiography Retrieval System
Viaarxiv icon

MedShift: identifying shift data for medical dataset curation

Dec 27, 2021
Figure 1 for MedShift: identifying shift data for medical dataset curation
Figure 2 for MedShift: identifying shift data for medical dataset curation
Figure 3 for MedShift: identifying shift data for medical dataset curation
Figure 4 for MedShift: identifying shift data for medical dataset curation
Viaarxiv icon

CVAD: A generic medical anomaly detector based on Cascade VAE

Add code
Oct 29, 2021
Figure 1 for CVAD: A generic medical anomaly detector based on Cascade VAE
Figure 2 for CVAD: A generic medical anomaly detector based on Cascade VAE
Figure 3 for CVAD: A generic medical anomaly detector based on Cascade VAE
Figure 4 for CVAD: A generic medical anomaly detector based on Cascade VAE
Viaarxiv icon

Margin-Aware Intra-Class Novelty Identification for Medical Images

Add code
Jul 31, 2021
Figure 1 for Margin-Aware Intra-Class Novelty Identification for Medical Images
Figure 2 for Margin-Aware Intra-Class Novelty Identification for Medical Images
Figure 3 for Margin-Aware Intra-Class Novelty Identification for Medical Images
Figure 4 for Margin-Aware Intra-Class Novelty Identification for Medical Images
Viaarxiv icon