collaborators

11 papers

cs.CV2025

TRIPS: Efficient Vision-and-Language Pre-training with Text-Relevant Image Patch Selection

Chaoya Jiang, Haiyang Xu, Chenliang Li +5

Vision Transformers (ViTs) have been widely used in large-scale Vision and Language Pre-training (VLP) models. Though previous VLP works have proved the effectiveness of ViTs, they…

cs.CV2025

Adaptively Clustering Neighbor Elements for Image-Text Generation

Zihua Wang, Xu Yang, Hanwang Zhang +4

We propose a novel Transformer-based image-to-text generation model termed as \textbf{ACF} that adaptively clusters vision patches into object regions and language words into phras…

cs.CV2024

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

Hongrui Jia, Chaoya Jiang, Haiyang Xu +6

As language models continue to scale, Large Language Models (LLMs) have exhibited emerging capabilities in In-Context Learning (ICL), enabling them to solve language tasks by prefi…

cs.AI2024

Hal-Eval: A Universal and Fine-grained Hallucination Evaluation Framework for Large Vision Language Models

Chaoya Jiang, Hongrui Jia, Wei Ye +5

Large Vision Language Models exhibit remarkable capabilities but struggle with hallucinations inconsistencies between images and their descriptions. Previous hallucination evaluati…

cs.CV2024

MIBench: Evaluating Multimodal Large Language Models over Multiple Images

Haowei Liu, Xi Zhang, Haiyang Xu +8

Built on the power of LLMs, numerous multimodal large language models (MLLMs) have recently achieved remarkable performance on various vision-language tasks. However, most existing…

cs.CV2024

mPLUG-DocOwl2: High-resolution Compressing for OCR-free Multi-page Document Understanding

Anwen Hu, Haiyang Xu, Liang Zhang +6

Multimodel Large Language Models(MLLMs) have achieved promising OCR-free Document Understanding performance by increasing the supported resolution of document images. However, this…