Pinned Loading

1. FlagOpen/FlagEmbedding FlagOpen/FlagEmbedding Public

   Retrieval and Retrieval-augmented LLMs

   Python 12.2k 916

2. MLVU MLVU Public

   🔥🔥MLVU: Multi-task Long Video Understanding Benchmark

   Python 268 6

3. VectorSpaceLab/MegaPairs VectorSpaceLab/MegaPairs Public

   [ACL 2025 Oral] 🔥🔥 MegaPairs: Massive Data Synthesis for Universal Multimodal Retrieval

   Jupyter Notebook 249 10

4. Tencent/WeMM-Embedding Tencent/WeMM-Embedding Public

   WeMM-Embedding is a family of universal multimodal embedding models by the WeChat Vision Team at Tencent, supporting multimodal understanding and retrieval.

   Python 1.5k 107

5. VISTA_Evaluation_FineTuning VISTA_Evaluation_FineTuning Public

   Evaluation code and datasets for the ACL 2024 paper, VISTA: Visualized Text Embedding for Universal Multi-Modal Retrieval. The original code and model can be accessed at FlagEmbedding.

   Python 48 2

6. VectorSpaceLab/OmniGen VectorSpaceLab/OmniGen Public

   OmniGen: Unified Image Generation. https://arxiv.org/pdf/2409.11340

   Jupyter Notebook 4.3k 363