Alibaba-NLP/gme-Qwen2-VL-2B-Instruct
Sentence Similarity
•
2B
•
Updated
•
89.2k
•
120
None defined yet.
Towards Universal Video Retrieval: Generalizing Video Embedding via Synthesized Multimodal Pyramid Curriculum
$\text{E}^2\text{Rank}$: Your Text Embedding can Also be an Effective and Efficient Listwise Reranker