Haiyang Xu

OpenReview

papers

1,189

total citations

papers (13)

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

CVPR 2024arXiv

614

citations

mPLUG-Owl3: Towards Long Image-Sequence Understanding in Multi-Modal Large Language Models

ICLR 2025arXiv

243

citations

Hallucination Augmented Contrastive Learning for Multimodal Large Language Model

CVPR 2024arXiv

121

citations

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

ICCV 2023arXiv

citations

EMScore: Evaluating Video Captioning via Coarse-Grained and Fine-Grained Embedding Matching

CVPR 2022arXiv

citations

Bayesian Diffusion Models for 3D Shape Reconstruction

CVPR 2024arXiv

citations

Science-T2I: Addressing Scientific Illusions in Image Synthesis

CVPR 2025arXiv

citations

BUS: Efficient and Effective Vision-Language Pre-Training with Bottom-Up Patch Summarization.

ICCV 2023arXiv

citations

DepR: Depth Guided Single-view Scene Reconstruction with Instance-level Diffusion

ICCV 2025arXiv

citations

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

CVPR 2025arXiv

citations

Haiyang Xu

papers (13)

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

mPLUG-Owl3: Towards Long Image-Sequence Understanding in Multi-Modal Large Language Models

Hallucination Augmented Contrastive Learning for Multimodal Large Language Model

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

EMScore: Evaluating Video Captioning via Coarse-Grained and Fine-Grained Embedding Matching

Bayesian Diffusion Models for 3D Shape Reconstruction

Science-T2I: Addressing Scientific Illusions in Image Synthesis

BUS: Efficient and Effective Vision-Language Pre-Training with Bottom-Up Patch Summarization.

DepR: Depth Guided Single-view Scene Reconstruction with Instance-level Diffusion

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

Learning Trajectory-Word Alignments for Video-Language Tasks

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

YOLO-Count: Differentiable Object Counting for Text-to-Image Generation

papers (13)

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

mPLUG-Owl3: Towards Long Image-Sequence Understanding in Multi-Modal Large Language Models

Hallucination Augmented Contrastive Learning for Multimodal Large Language Model

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

EMScore: Evaluating Video Captioning via Coarse-Grained and Fine-Grained Embedding Matching

Bayesian Diffusion Models for 3D Shape Reconstruction

Science-T2I: Addressing Scientific Illusions in Image Synthesis

BUS: Efficient and Effective Vision-Language Pre-Training with Bottom-Up Patch Summarization.

DepR: Depth Guided Single-view Scene Reconstruction with Instance-level Diffusion

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

Learning Trajectory-Word Alignments for Video-Language Tasks

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

YOLO-Count: Differentiable Object Counting for Text-to-Image Generation