168 citations · 467 across the 47 of their papers we have counts for
23 papers · 1 filter
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…
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…
mPLUG-Owl3: Towards Long Image-Sequence Understanding in Multi-Modal Large Language Models
Jiabo Ye, Haiyang Xu, Haowei Liu +6
Multi-modal Large Language Models (MLLMs) have demonstrated remarkable capabilities in executing instructions for a variety of single-image tasks. Despite this progress, significan…
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…
TinyChart: Efficient Chart Understanding with Visual Token Merging and Program-of-Thoughts Learning
Liang Zhang, Anwen Hu, Haiyang Xu +5
Charts are important for presenting and explaining complex data relationships. Recently, multimodal large language models (MLLMs) have shown remarkable capabilities in various char…
mPLUG-DocOwl 1.5: Unified Structure Learning for OCR-free Document Understanding
Anwen Hu, Haiyang Xu, Jiabo Ye +8
Structure information is critical for understanding the semantics of text-rich images, such as documents, tables, and charts. Existing Multimodal Large Language Models (MLLMs) for…
Efficient Vision-and-Language Pre-training with Text-Relevant Image Patch Selection
Wei Ye, Chaoya Jiang, Haiyang Xu +6
Vision Transformers (ViTs) have become increasingly popular in large-scale Vision and Language Pre-training (VLP) models. Although previous VLP research has demonstrated the effica…
Semantics-enhanced Cross-modal Masked Image Modeling for Vision-Language Pre-training
Haowei Liu, Yaya Shi, Haiyang Xu +8
In vision-language pre-training (VLP), masked image modeling (MIM) has recently been introduced for fine-grained cross-modal alignment. However, in most existing methods, the recon…
Unifying Latent and Lexicon Representations for Effective Video-Text Retrieval
Haowei Liu, Yaya Shi, Haiyang Xu +8
In video-text retrieval, most existing methods adopt the dual-encoder architecture for fast retrieval, which employs two individual encoders to extract global latent representation…
Hallucination Augmented Contrastive Learning for Multimodal Large Language Model
Chaoya Jiang, Haiyang Xu, Mengfan Dong +7
Multi-modal large language models (MLLMs) have been shown to efficiently integrate natural language with visual information to handle multi-modal tasks. However, MLLMs still face a…
UReader: Universal OCR-free Visually-situated Language Understanding with Multimodal Large Language Model
Jiabo Ye, Anwen Hu, Haiyang Xu +11
Text is ubiquitous in our visual world, conveying crucial information, such as in documents, websites, and everyday photographs. In this work, we propose UReader, a first explorati…
BUS:Efficient and Effective Vision-language Pre-training with Bottom-Up Patch Summarization
Chaoya Jiang, Haiyang Xu, Wei Ye +7
Vision Transformer (ViT) based Vision-Language Pre-training (VLP) models have demonstrated impressive performance in various tasks. However, the lengthy visual token sequences fed…
Vision Transformer with Attention Map Hallucination and FFN Compaction
Haiyang Xu, Zhichao Zhou, Dongliang He +2
Vision Transformer(ViT) is now dominating many vision tasks. The drawback of quadratic complexity of its token-wise multi-head self-attention (MHSA), is extensively addressed via e…
Youku-mPLUG: A 10 Million Large-scale Chinese Video-Language Dataset for Pre-training and Benchmarks
Haiyang Xu, Qinghao Ye, Xuan Wu +13
To promote the development of Vision-Language Pre-training (VLP) and multimodal Large Language Model (LLM) in the Chinese community, we firstly release the largest public Chinese h…
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…
Transforming Visual Scene Graphs to Image Captions
Xu Yang, Jiawei Peng, Zihua Wang +7
We propose to Transform Scene Graphs (TSG) into more descriptive captions. In TSG, we apply multi-head attention (MHA) to design the Graph Neural Network (GNN) for embedding scene…
mPLUG-2: A Modularized Multi-modal Foundation Model Across Text, Image and Video
Haiyang Xu, Qinghao Ye, Ming Yan +12
Recent years have witnessed a big convergence of language, vision, and multi-modal pretraining. In this work, we present mPLUG-2, a new unified paradigm with modularized design for…
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…
Learning Trajectory-Word Alignments for Video-Language Tasks
Xu Yang, Zhangzikang Li, Haiyang Xu +7
In a video, an object usually appears as the trajectory, i.e., it spans over a few spatial but longer temporal patches, that contains abundant spatiotemporal contexts. However, mod…
HiTeA: Hierarchical Temporal-Aware Video-Language Pre-training
Qinghao Ye, Guohai Xu, Ming Yan +4
Video-language pre-training has advanced the performance of various downstream video-language tasks. However, most previous methods directly inherit or adapt typical image-language…
Image Captioning In the Transformer Age
Yang Xu, Li Li, Haiyang Xu +3
Image Captioning (IC) has achieved astonishing developments by incorporating various techniques into the CNN-RNN encoder-decoder architecture. However, since CNN and RNN do not sha…
EMScore: Evaluating Video Captioning via Coarse-Grained and Fine-Grained Embedding Matching
Yaya Shi, Xu Yang, Haiyang Xu +4
Current metrics for video captioning are mostly based on the text-level comparison between reference and candidate captions. However, they have some insuperable drawbacks, e.g., th…
E2E-VLP: End-to-End Vision-Language Pre-training Enhanced by Visual Learning
Haiyang Xu, Ming Yan, Chenliang Li +4
Vision-language pre-training (VLP) on large-scale image-text pairs has achieved huge success for the cross-modal downstream tasks. The most existing pre-training methods mainly ado…