opendatalab / OHR-BenchLinks
OCR Hinders RAG: Evaluating the Cascading Impact of OCR on Retrieval-Augmented Generation
☆75Updated 2 months ago
Alternatives and similar repositories for OHR-Bench
Users that are interested in OHR-Bench are comparing it to the libraries listed below
Sorting:
- ☆93Updated 3 months ago
- ☆83Updated 3 weeks ago
- This is the code repo for our paper "Benchmarking Retrieval-Augmented Generation in Multi-Modal Contexts".☆32Updated 2 months ago
- An implementation of "M3DOCRAG: Multi-modal Retrieval is What You Need for Multi-page Multi-document Understanding" by Jaemin Cho, Debanj…☆36Updated 6 months ago
- ☆223Updated last week
- Agentic Reward Modeling: Integrating Human Preferences with Verifiable Correctness Signals for Reliable Reward Systems☆90Updated 2 months ago
- Official repo for "LongRAG: Enhancing Retrieval-Augmented Generation with Long-context LLMs".☆231Updated 9 months ago
- Code for Paper: Harnessing Webpage Uis For Text Rich Visual Understanding☆51Updated 5 months ago
- Code & Dataset for Paper: "Distill Visual Chart Reasoning Ability from LLMs to MLLMs"☆53Updated 7 months ago
- This is the code repo for our paper "Autonomously Knowledge Assimilation and Accommodation through Retrieval-Augmented Agents".☆106Updated 7 months ago
- ☆45Updated 2 weeks ago
- ACL 2025: Synthetic data generation pipelines for text-rich images.☆73Updated 3 months ago
- Official repository for RAGViz: Diagnose and Visualize Retrieval-Augmented Generation [EMNLP 2024]☆83Updated 4 months ago
- ☆102Updated last month
- [ICML 2025] Programming Every Example: Lifting Pre-training Data Quality Like Experts at Scale☆248Updated 3 weeks ago
- A new novel multi-modality (Vision) RAG architecture☆27Updated 8 months ago
- Repository for “PlanRAG: A Plan-then-Retrieval Augmented Generation for Generative Large Language Models as Decision Makers”, NAACL24☆138Updated 11 months ago
- MDocAgent: A Multi-Modal Multi-Agent Framework for Document Understanding☆161Updated 2 months ago
- ☆142Updated last year
- This project is a collection of fine-tuning scripts to help researchers fine-tune Qwen 2 VL on HuggingFace datasets.☆69Updated 8 months ago
- SELF-GUIDE: Better Task-Specific Instruction Following via Self-Synthetic Finetuning. COLM 2024 Accepted Paper☆32Updated last year
- ☆92Updated 2 months ago
- InstructDoc: A Dataset for Zero-Shot Generalization of Visual Document Understanding with Instructions (AAAI2024)☆160Updated last year
- The official repository for "2.5 Years in Class: A Multimodal Textbook for Vision-Language Pretraining"☆158Updated 2 months ago
- ☆55Updated 6 months ago
- This is the repo for the paper "PANGEA: A FULLY OPEN MULTILINGUAL MULTIMODAL LLM FOR 39 LANGUAGES"☆105Updated 6 months ago
- official code for "Fox: Focus Anywhere for Fine-grained Multi-page Document Understanding"☆149Updated last year
- Meta-Chunking: Learning Efficient Text Segmentation via Logical Perception☆171Updated this week
- ☆89Updated last week
- Ruler: A Model-Agnostic Method to Control Generated Length for Large Language Models☆35Updated 8 months ago