opendatalab / MLLM-DataEngineLinks
MLLM-DataEngine: An Iterative Refinement Approach for MLLM
☆47Updated last year
Alternatives and similar repositories for MLLM-DataEngine
Users that are interested in MLLM-DataEngine are comparing it to the libraries listed below
Sorting:
- [NeurIPS-24] This is the official implementation of the paper "DeepStack: Deeply Stacking Visual Tokens is Surprisingly Simple and Effect…☆39Updated last year
- [NeurIPS 2024] Vision Model Pre-training on Interleaved Image-Text Data via Latent Compression Learning☆70Updated 6 months ago
- ☆119Updated last year
- ☆91Updated last year
- The proposed simulated dataset consisting of 9,536 charts and associated data annotations in CSV format.☆26Updated last year
- Lion: Kindling Vision Intelligence within Large Language Models☆52Updated last year
- ☆19Updated last year
- A huge dataset for Document Visual Question Answering☆19Updated last year
- A collection of visual instruction tuning datasets.☆76Updated last year
- ☆133Updated last year
- WeThink: Toward General-purpose Vision-Language Reasoning via Reinforcement Learning☆34Updated 2 months ago
- ☆31Updated last year
- ☆65Updated last year
- ☆87Updated last year
- Pink: Unveiling the Power of Referential Comprehension for Multi-modal LLMs☆91Updated 7 months ago
- [SCIS 2024] The official implementation of the paper "MMInstruct: A High-Quality Multi-Modal Instruction Tuning Dataset with Extensive Di…☆55Updated 9 months ago
- Official repository of "CoMP: Continual Multimodal Pre-training for Vision Foundation Models"☆30Updated 4 months ago
- [NeurIPS 2024] Needle In A Multimodal Haystack (MM-NIAH): A comprehensive benchmark designed to systematically evaluate the capability of…☆115Updated 9 months ago
- SVIT: Scaling up Visual Instruction Tuning☆164Updated last year
- Scaling Multi-modal Instruction Fine-tuning with Tens of Thousands Vision Task Types☆27Updated last month
- ☆86Updated 7 months ago
- Repository of paper: Position-Enhanced Visual Instruction Tuning for Multimodal Large Language Models☆37Updated last year
- OpenThinkIMG is an end-to-end open-source framework that empowers Large Vision-Language Models to think with images.☆74Updated last month
- (ACL 2025) MAmmoTH-VL: Eliciting Multimodal Reasoning with Instruction Tuning at Scale☆48Updated 2 months ago
- VL-GPT: A Generative Pre-trained Transformer for Vision and Language Understanding and Generation☆86Updated 11 months ago
- Official code for "What Makes for Good Visual Tokenizers for Large Language Models?".☆58Updated 2 years ago
- [NeurIPS'24] Official PyTorch Implementation of Seeing the Image: Prioritizing Visual Correlation by Contrastive Alignment☆57Updated 11 months ago
- ☆45Updated 7 months ago
- Official repository of MMDU dataset☆93Updated 10 months ago
- The official GitHub page for ''What Makes for Good Visual Instructions? Synthesizing Complex Visual Reasoning Instructions for Visual Ins…☆19Updated last year