Letian2003 / MM_INFLinks
An efficient multi-modal instruction-following data synthesis tool and the official implementation of Oasis https://arxiv.org/abs/2503.08741.
☆37Updated 8 months ago
Alternatives and similar repositories for MM_INF
Users that are interested in MM_INF are comparing it to the libraries listed below
Sorting:
- MLLM-DataEngine: An Iterative Refinement Approach for MLLM☆48Updated last year
- A subset of YFCC100M. Tools, checking scripts and links of web drive to download datasets(uncompressed).☆19Updated last year
- ChineseCLIP using online learning☆13Updated 3 years ago
- Large Multimodal Model☆15Updated last year
- MTVQA: Benchmarking Multilingual Text-Centric Visual Question Answering. A comprehensive evaluation of multimodal large model multilingua…☆63Updated 8 months ago
- A multimodal large-scale model, which performs close to the closed-source Qwen-VL-PLUS on many datasets and significantly surpasses the p…☆14Updated 2 years ago
- Lion: Kindling Vision Intelligence within Large Language Models☆51Updated 2 years ago
- Our 2nd-gen LMM☆34Updated last year
- [ACM MM2025] The official repository for the RealSyn dataset☆40Updated last month
- A huge dataset for Document Visual Question Answering☆20Updated last year
- "Towards Improving Document Understanding: An Exploration on Text-Grounding via MLLMs" 2023☆16Updated last year
- ☆88Updated last year
- Toward Universal Multimodal Embedding☆73Updated 6 months ago
- ☆92Updated 2 years ago
- The SAIL-VL2 series model developed by the BytedanceDouyinContent Group☆76Updated 4 months ago
- ☆75Updated last year
- Exploring Efficient Fine-Grained Perception of Multimodal Large Language Models☆65Updated last year
- Fully Open Framework for Democratized Multimodal Reinforcement Learning.☆39Updated last month
- Scaling Multi-modal Instruction Fine-tuning with Tens of Thousands Vision Task Types☆33Updated 6 months ago
- Chinese CLIP models with SOTA performance.☆60Updated 2 years ago
- A Dead Simple and Modularized Multi-Modal Training and Finetune Framework. Compatible to any LLaVA/Flamingo/QwenVL/MiniGemini etc series …☆19Updated last year
- The proposed simulated dataset consisting of 9,536 charts and associated data annotations in CSV format.☆26Updated last year
- ☆57Updated 2 years ago
- The huggingface implementation of Fine-grained Late-interaction Multi-modal Retriever.☆105Updated 8 months ago
- ☆16Updated 2 years ago
- OpenThinkIMG is an end-to-end open-source framework that empowers Large Vision-Language Models to think with images.☆114Updated 7 months ago
- ☆124Updated last year
- This project aims to collect and collate various datasets for multimodal large model training, including but not limited to pre-training …☆68Updated 9 months ago
- ☆72Updated 2 years ago
- ☆19Updated 2 years ago