Letian2003 / MM_INFLinks
An efficient multi-modal instruction-following data synthesis tool and the official implementation of Oasis https://arxiv.org/abs/2503.08741.
☆35Updated 7 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
- Large Multimodal Model☆15Updated last year
- ChineseCLIP using online learning☆13Updated 3 years ago
- A subset of YFCC100M. Tools, checking scripts and links of web drive to download datasets(uncompressed).☆19Updated last year
- "Towards Improving Document Understanding: An Exploration on Text-Grounding via MLLMs" 2023☆16Updated last year
- [ACM MM2025] The official repository for the RealSyn dataset☆39Updated 3 weeks 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 last year
- Lion: Kindling Vision Intelligence within Large Language Models☆51Updated last year
- The SAIL-VL2 series model developed by the BytedanceDouyinContent Group☆76Updated 3 months ago
- ☆92Updated 2 years ago
- survery of small language models☆17Updated last year
- Toward Universal Multimodal Embedding☆74Updated 5 months ago
- Scaling Multi-modal Instruction Fine-tuning with Tens of Thousands Vision Task Types☆32Updated 5 months ago
- Fully Open Framework for Democratized Multimodal Reinforcement Learning.☆33Updated 3 weeks ago
- ☆19Updated 2 years ago
- ☆87Updated last year
- Our 2nd-gen LMM☆34Updated last year
- ☆75Updated last year
- Chinese CLIP models with SOTA performance.☆59Updated 2 years ago
- [CVPR 2024] DiffAgent: Fast and Accurate Text-to-Image API Selection with Large Language Model☆18Updated last year
- Margin-based Vision Transformer☆61Updated last month
- A huge dataset for Document Visual Question Answering☆20Updated last year
- MTVQA: Benchmarking Multilingual Text-Centric Visual Question Answering. A comprehensive evaluation of multimodal large model multilingua…☆63Updated 7 months ago
- A Dead Simple and Modularized Multi-Modal Training and Finetune Framework. Compatible to any LLaVA/Flamingo/QwenVL/MiniGemini etc series …☆19Updated last year
- OpenThinkIMG is an end-to-end open-source framework that empowers Large Vision-Language Models to think with images.☆108Updated 5 months ago
- The proposed simulated dataset consisting of 9,536 charts and associated data annotations in CSV format.☆26Updated last year
- A handwritten Chemical Structure Image data set named EDU-CHEMC, which consists of totally 52,987 handwritten molecular structure images …☆14Updated 7 months ago
- ☆124Updated last year
- [PR 2024] A large Cross-Modal Video Retrieval Dataset with Reading Comprehension☆28Updated 2 years ago
- ☆16Updated 2 years ago