Qingpei Guo

papers

104

total citations

papers (12)

Pink: Unveiling the Power of Referential Comprehension for Multi-modal LLMs

CVPR 2024arXiv

citations

Boundary-Aware Backward-Compatible Representation via Adversarial Learning in Image Retrieval

CVPR 2023arXiv

citations

SegAgent: Exploring Pixel Understanding Capabilities in MLLMs by Imitating Human Annotator Trajectories

CVPR 2025arXiv

citations

SyCoCa: Symmetrizing Contrastive Captioners with Attentive Masking for Multimodal Alignment

ICML 2024arXiv

citations

Switch-BERT: Learning to Model Multimodal Interactions by Switching Attention and Input

ECCV 2022arXiv

citations

DynFocus: Dynamic Cooperative Network Empowers LLMs with Video Understanding

CVPR 2025arXiv

citations

Social Debiasing for Fair Multi-modal LLMs

ICCV 2025arXiv

citations

CNVid-3.5M: Build, Filter, and Pre-Train the Large-Scale Public Chinese Video-Text Dataset

CVPR 2023

citations

Qingpei Guo

papers (12)

Pink: Unveiling the Power of Referential Comprehension for Multi-modal LLMs

Boundary-Aware Backward-Compatible Representation via Adversarial Learning in Image Retrieval

SegAgent: Exploring Pixel Understanding Capabilities in MLLMs by Imitating Human Annotator Trajectories

SyCoCa: Symmetrizing Contrastive Captioners with Attentive Masking for Multimodal Alignment

Switch-BERT: Learning to Model Multimodal Interactions by Switching Attention and Input

DynFocus: Dynamic Cooperative Network Empowers LLMs with Video Understanding

Social Debiasing for Fair Multi-modal LLMs

CNVid-3.5M: Build, Filter, and Pre-Train the Large-Scale Public Chinese Video-Text Dataset

LPSNet: A Lightweight Solution for Fast Panoptic Segmentation

Engage for All: Making Ordinary Image Descriptions Appealing Again!

Unified Video Generation via Next-Set Prediction in Continuous Domain

Attributive Reasoning for Hallucination Diagnosis of Large Language Models

papers (12)

Pink: Unveiling the Power of Referential Comprehension for Multi-modal LLMs

Boundary-Aware Backward-Compatible Representation via Adversarial Learning in Image Retrieval

SegAgent: Exploring Pixel Understanding Capabilities in MLLMs by Imitating Human Annotator Trajectories

SyCoCa: Symmetrizing Contrastive Captioners with Attentive Masking for Multimodal Alignment

Switch-BERT: Learning to Model Multimodal Interactions by Switching Attention and Input

DynFocus: Dynamic Cooperative Network Empowers LLMs with Video Understanding

Social Debiasing for Fair Multi-modal LLMs

CNVid-3.5M: Build, Filter, and Pre-Train the Large-Scale Public Chinese Video-Text Dataset

LPSNet: A Lightweight Solution for Fast Panoptic Segmentation

Engage for All: Making Ordinary Image Descriptions Appealing Again!

Unified Video Generation via Next-Set Prediction in Continuous Domain

Attributive Reasoning for Hallucination Diagnosis of Large Language Models