Ji Zhang

OpenReview

Affiliations

Alibaba

papers

1,099

total citations

papers (14)

mPLUG-Owl2: Revolutionizing Multi-modal Large Language Model with Modality Collaboration

CVPR 2024arXiv

614

citations

Hallucination Augmented Contrastive Learning for Multimodal Large Language Model

CVPR 2024arXiv

121

citations

Shifting More Attention to Visual Backbone: Query-Modulated Refinement Networks for End-to-End Visual Grounding

CVPR 2022arXiv

citations

Skip Tuning: Pre-trained Vision-Language Models are Effective and Efficient Adapters Themselves

CVPR 2025arXiv

citations

A Simple yet Effective Layout Token in Large Language Models for Document Understanding

CVPR 2025arXiv

citations

SymDPO: Boosting In-Context Learning of Large Multimodal Models with Symbol Demonstration Direct Preference Optimization

CVPR 2025arXiv

citations

AdaMMS: Model Merging for Heterogeneous Multimodal Large Language Models with Unsupervised Coefficient Optimization

CVPR 2025arXiv

citations

TiMix: Text-Aware Image Mixing for Effective Vision-Language Pre-training

AAAI 2024arXiv

citations

MOSAIC: Generating Consistent, Privacy-Preserving Scenes from Multiple Depth Views in Multi-Room Environments

ICCV 2025arXiv

citations

Accurate Few-Shot Object Detection With Support-Query Mutual Guidance and Hybrid Loss

CVPR 2021

citations

Ji Zhang

Affiliations

papers (14)

mPLUG-Owl2: Revolutionizing Multi-modal Large Language Model with Modality Collaboration

Hallucination Augmented Contrastive Learning for Multimodal Large Language Model

Shifting More Attention to Visual Backbone: Query-Modulated Refinement Networks for End-to-End Visual Grounding

HiTeA: Hierarchical Temporal-Aware Video-Language Pre-training

DePT: Decoupled Prompt Tuning

SubT-MRS Dataset: Pushing SLAM Towards All-weather Environments

DETA: Denoised Task Adaptation for Few-Shot Learning

Skip Tuning: Pre-trained Vision-Language Models are Effective and Efficient Adapters Themselves

A Simple yet Effective Layout Token in Large Language Models for Document Understanding

SymDPO: Boosting In-Context Learning of Large Multimodal Models with Symbol Demonstration Direct Preference Optimization

AdaMMS: Model Merging for Heterogeneous Multimodal Large Language Models with Unsupervised Coefficient Optimization

TiMix: Text-Aware Image Mixing for Effective Vision-Language Pre-training

MOSAIC: Generating Consistent, Privacy-Preserving Scenes from Multiple Depth Views in Multi-Room Environments

Accurate Few-Shot Object Detection With Support-Query Mutual Guidance and Hybrid Loss

papers (14)

mPLUG-Owl2: Revolutionizing Multi-modal Large Language Model with Modality Collaboration

Hallucination Augmented Contrastive Learning for Multimodal Large Language Model

Shifting More Attention to Visual Backbone: Query-Modulated Refinement Networks for End-to-End Visual Grounding

HiTeA: Hierarchical Temporal-Aware Video-Language Pre-training

DePT: Decoupled Prompt Tuning

SubT-MRS Dataset: Pushing SLAM Towards All-weather Environments

DETA: Denoised Task Adaptation for Few-Shot Learning

Skip Tuning: Pre-trained Vision-Language Models are Effective and Efficient Adapters Themselves

A Simple yet Effective Layout Token in Large Language Models for Document Understanding

SymDPO: Boosting In-Context Learning of Large Multimodal Models with Symbol Demonstration Direct Preference Optimization

AdaMMS: Model Merging for Heterogeneous Multimodal Large Language Models with Unsupervised Coefficient Optimization

TiMix: Text-Aware Image Mixing for Effective Vision-Language Pre-training

MOSAIC: Generating Consistent, Privacy-Preserving Scenes from Multiple Depth Views in Multi-Room Environments

Accurate Few-Shot Object Detection With Support-Query Mutual Guidance and Hybrid Loss