195 citations · 936 across the 38 of their papers we have counts for
38 papers
PaddleOCR-VL-1.6: Expanding the Frontier of Document Parsing with Under-Optimized Region Refinement and Progressive Post-Training
Zelun Zhang, Hongen Liu, Suyin Liang +12
We introduce PaddleOCR-VL-1.6, an upgraded compact document parsing model built upon PaddleOCR-VL-1.5. Although PaddleOCR-VL-1.5 establishes a strong 0.9B baseline, its remaining e…
Boosting Document Parsing Efficiency and Performance with Coarse-to-Fine Visual Processing
Cheng Cui, Ting Sun, Suyin Liang +15
Document parsing is a fine-grained task where image resolution significantly impacts performance. While advanced research leveraging vision-language models benefits from high-resol…
PaddleOCR-VL-1.5: Towards a Multi-Task 0.9B VLM for Robust In-the-Wild Document Parsing
Cheng Cui, Ting Sun, Suyin Liang +12
We introduce PaddleOCR-VL-1.5, an upgraded model achieving a new state-of-the-art (SOTA) accuracy of 94.5% on OmniDocBench v1.5. To rigorously evaluate robustness against real-worl…
PaddleOCR-VL: Boosting Multilingual Document Parsing via a 0.9B Ultra-Compact Vision-Language Model
Cheng Cui, Ting Sun, Suyin Liang +15
In this report, we propose PaddleOCR-VL, a SOTA and resource-efficient model tailored for document parsing. Its core component is PaddleOCR-VL-0.9B, a compact yet powerful vision-l…
GraphNet: A Large-Scale Computational Graph Dataset for Tensor Compiler Research
Xinqi Li, Yiqun Liu, Shan Jiang +6
We introduce GraphNet, a dataset of 2.7K real-world deep learning computational graphs with rich metadata, spanning six major task categories across multiple deep learning framewor…
CCQ: Convolutional Code for Extreme Low-bit Quantization in LLMs
Zhaojing Zhou, Xunchao Li, Minghao Li +8
The rapid scaling of Large Language Models (LLMs) elevates inference costs and compounds substantial deployment barriers. While quantization to 8 or 4 bits mitigates this, sub-3-bi…
PaddleOCR 3.0 Technical Report
Cheng Cui, Ting Sun, Manhui Lin +16
This technical report introduces PaddleOCR 3.0, an Apache-licensed open-source toolkit for OCR and document parsing. To address the growing demand for document understanding in the…
Spectral Heterogeneous Graph Convolutions via Positive Noncommutative Polynomials
Mingguo He, Zhewei Wei, Shikun Feng +4
Heterogeneous Graph Neural Networks (HGNNs) have gained significant popularity in various heterogeneous graph learning tasks. However, most existing HGNNs rely on spatial domain-ba…
Label Information Enhanced Fraud Detection against Low Homophily in Graphs
Yuchen Wang, Jinghui Zhang, Zhengjie Huang +9
Node classification is a substantial problem in graph-based fraud detection. Many existing works adopt Graph Neural Networks (GNNs) to enhance fraud detectors. While promising, cur…
TA-MoE: Topology-Aware Large Scale Mixture-of-Expert Training
Chang Chen, Min Li, Zhihua Wu +2
Sparsely gated Mixture-of-Expert (MoE) has demonstrated its effectiveness in scaling up deep neural networks to an extreme scale. Despite that numerous efforts have been made to im…
PP-YOLOE-R: An Efficient Anchor-Free Rotated Object Detector
Xinxin Wang, Guanzhong Wang, Qingqing Dang +3
Arbitrary-oriented object detection is a fundamental task in visual scenes involving aerial images and scene text. In this report, we present PP-YOLOE-R, an efficient anchor-free r…
Efficient AlphaFold2 Training using Parallel Evoformer and Branch Parallelism
Guoxia Wang, Zhihua Wu, Xiaomin Fang +4
The accuracy of AlphaFold2, a frontier end-to-end structure prediction system, is already close to that of the experimental determination techniques. Due to the complex model archi…
PP-StructureV2: A Stronger Document Analysis System
Chenxia Li, Ruoyu Guo, Jun Zhou +6
A large amount of document data exists in unstructured form such as raw images without any text information. Designing a practical document image analysis system is a meaningful bu…
ERNIE-mmLayout: Multi-grained MultiModal Transformer for Document Understanding
Wenjin Wang, Zhengjie Huang, Bin Luo +8
Recent efforts of multimodal Transformers have improved Visually Rich Document Understanding (VrDU) tasks via incorporating visual and textual information. However, existing approa…
Boosting Distributed Training Performance of the Unpadded BERT Model
Jinle Zeng, Min Li, Zhihua Wu +4
Pre-training models are an important tool in Natural Language Processing (NLP), while the BERT model is a classic pre-training model whose structure has been widely adopted by foll…
Large-scale Knowledge Distillation with Elastic Heterogeneous Computing Resources
Ji Liu, Daxiang Dong, Xi Wang +5
Although more layers and more parameters generally improve the accuracy of the models, such big models generally have high computational complexity and require big memory, which ex…
HelixFold: An Efficient Implementation of AlphaFold2 using PaddlePaddle
Guoxia Wang, Xiaomin Fang, Zhihua Wu +6
Accurate protein structure prediction can significantly accelerate the development of life science. The accuracy of AlphaFold2, a frontier end-to-end structure prediction system, i…
PP-OCRv3: More Attempts for the Improvement of Ultra Lightweight OCR System
Chenxia Li, Weiwei Liu, Ruoyu Guo +9
Optical character recognition (OCR) technology has been widely used in various scenes, as shown in Figure 1. Designing a practical OCR system is still a meaningful but challenging…
PaddleSpeech: An Easy-to-Use All-in-One Speech Toolkit
Hui Zhang, Tian Yuan, Junkun Chen +10
PaddleSpeech is an open-source all-in-one speech toolkit. It aims at facilitating the development and research of speech processing technologies by providing an easy-to-use command…
Nebula-I: A General Framework for Collaboratively Training Deep Learning Models on Low-Bandwidth Cloud Clusters
Yang Xiang, Zhihua Wu, Weibao Gong +15
The ever-growing model size and scale of compute have attracted increasing interests in training deep learning models over multiple nodes. However, when it comes to training on clo…
Simple and Effective Relation-based Embedding Propagation for Knowledge Representation Learning
Huijuan Wang, Siming Dai, Weiyue Su +7
Relational graph neural networks have garnered particular attention to encode graph context in knowledge graphs (KGs). Although they achieved competitive performance on small KGs,…
MoESys: A Distributed and Efficient Mixture-of-Experts Training and Inference System for Internet Services
Dianhai Yu, Liang Shen, Hongxiang Hao +5
While modern internet services, such as chatbots, search engines, and online advertising, demand the use of large-scale deep neural networks (DNNs), distributed training and infere…
PP-Matting: High-Accuracy Natural Image Matting
Guowei Chen, Yi Liu, Jian Wang +11
Natural image matting is a fundamental and challenging computer vision task. It has many applications in image editing and composition. Recently, deep learning-based approaches hav…
PP-LiteSeg: A Superior Real-Time Semantic Segmentation Model
Juncai Peng, Yi Liu, Shiyu Tang +13
Real-world applications have high demands for semantic segmentation methods. Although semantic segmentation has made remarkable leap-forwards with deep learning, the performance of…