shi-yx / URaGView external linksLinks
Official implementation of URaG: Unified Retrieval and Generation in Multimodal LLMs for Efficient Long Document Understanding (AAAI 2026 Oral).
☆35Feb 4, 2026Updated last week
Alternatives and similar repositories for URaG
Users that are interested in URaG are comparing it to the libraries listed below
Sorting:
- The official implement of CTRNet++.☆14Dec 30, 2024Updated last year
- Read Ten Lines at One Glance: Line-Aware Semi-Autoregressive Transformer for Multi-Line Handwritten Mathematical Expression Recognition☆28Aug 29, 2023Updated 2 years ago
- [MM'2024] Official release of RFUND introduced in the MM'2024 paper "PEneo: Unifying Line Extraction, Line Grouping, and Entity Linking f…☆20Dec 4, 2024Updated last year
- [AAAI 2025] DocKylin: A Large Multimodal Model for Visual Document Understanding with Efficient Visual Slimming☆36Jun 1, 2025Updated 8 months ago
- ☆31Dec 18, 2025Updated last month
- Evaluation of the Optical Character Recognition (OCR) capabilities of GPT-4V(ision)☆126Nov 13, 2023Updated 2 years ago
- [ACM MM 2022] Marior: Margin Removal and Iterative Content Rectification for Document Dewarping in the Wild☆25Aug 12, 2022Updated 3 years ago
- [ICLR 2026] OCR-Reasoning Benchmark: Unveiling the True Capabilities of MLLMs in Complex Text-Rich Image Reasoning☆72Dec 17, 2025Updated last month
- [CVPR 2025] DocLayLLM: An Efficient Multi-modal Extension of Large Language Models for Text-rich Document Understanding☆26Dec 18, 2025Updated last month
- An unofficial PyTorch implementation of "Lin et al. ViBERTgrid: A Jointly Trained Multi-Modal 2D Document Representation for Key Informat…☆53Jan 9, 2024Updated 2 years ago
- ☆19Sep 11, 2024Updated last year
- (ICCV 2023) ESTextSpotter: Towards Better Scene Text Spotting with Explicit Synergy in Transformer☆78Apr 9, 2024Updated last year
- Repository for the KVP10k dataset☆22Sep 18, 2025Updated 4 months ago
- Pytorch implementation for "Implicit Feature Alignment: Learn to Convert Text Recognizer to Text Spotter".☆67Jun 15, 2021Updated 4 years ago
- [EMNLP 2024] TongGu, a classical Chinese language model.☆58Sep 28, 2024Updated last year
- [TAI 2023] Appearance Enhancement for Camera-captured Document Images in the Wild☆51Aug 28, 2025Updated 5 months ago
- The paper list of multilingual pre-trained models (Continual Updated).☆24Jun 18, 2024Updated last year
- Official implementation of UPOCR: Towards unified pixel-level OCR interface (ICML 2024)☆66Jun 6, 2024Updated last year
- Cookbook for Crafting Good Code☆57Mar 19, 2024Updated last year
- Official implementation of ViTEraser: Harnessing the Power of Vision Transformers for Scene Text Removal with SegMIM Pretraining (AAAI 20…☆62Jul 4, 2024Updated last year
- ☆11Jun 3, 2025Updated 8 months ago
- Contrast-guided Feature Adjustment Module for Visual Information Extraction☆30May 23, 2023Updated 2 years ago
- Pytorch Implementation of Chargrid Paper (https://arxiv.org/abs/1809.08799)☆27Mar 11, 2022Updated 3 years ago
- (CVPR 2024) Bridging the Gap Between End-to-End and Two-Step Text Spotting.☆71Jun 11, 2024Updated last year
- VimTS: A Unified Video and Image Text Spotter☆78Nov 10, 2024Updated last year
- Virtual news production using Tacotron2 and Wav2Lip☆11Nov 14, 2023Updated 2 years ago
- Official implementation of SPTS: Single-Point Text Spotting (ACM MM 2022 Oral)☆144Jul 26, 2023Updated 2 years ago
- [AAAI2025 Oral] Predicting the Original Appearance of Damaged Historical Documents☆102Jul 15, 2025Updated 7 months ago
- Official implementation of PageNet (IJCV 2022)☆81Oct 31, 2022Updated 3 years ago
- The dataset used in the CVPR 2022 paper (SimAN: Exploring Self-Supervised Representation Learning of Scene Text via Similarity-Aware Norm…☆34Jun 21, 2022Updated 3 years ago
- [NeurIPS 2022 Spotlight] The official GitHub page of "MSDS: A Large-Scale Chinese Signature and Token Digit String Dataset for Handwritin…☆91Aug 3, 2025Updated 6 months ago
- ☆156May 8, 2025Updated 9 months ago
- ☆82Jun 29, 2023Updated 2 years ago
- RoDLA: Benchmarking the Robustness of Document Layout Analysis Models☆38Mar 26, 2025Updated 10 months ago
- TensorRT In Docker☆11Dec 7, 2024Updated last year
- automatic music transcription application written in java☆12Jan 13, 2013Updated 13 years ago
- [CVPR 2025] Adaptive Markup Language Generation for Contextually-Grounded Visual Document Understanding☆15Jun 16, 2025Updated 8 months ago
- VexFS is a Linux kernel-native file system with built-in vector search and semantic memory. Designed for AI agents, RAG, and LLM workload…☆24Oct 19, 2025Updated 3 months ago
- An open-source platform for building and deploying real-time, low-latency AI voice agents for call automation for marketing.☆18Oct 16, 2025Updated 4 months ago