MMEB-v-2

MMEB-V2 (Massive Multimodal Embedding Benchmark) Website |Github | 🏆Leaderboard | 📖MMEB-V2/VLM2Vec-V2 Paper | | 📖MMEB-V1/VLM2Vec-V1 Paper | Introduction Building upon on our original MMEB, MMEB-V2 expands the evaluation scope to include five new tasks: four video-based tasks — Video Retrieval, Moment Retrieval, Vide

Papers using MMEB-v-2 (4)

PLUME: Latent Reasoning Based Universal Multimodal Embedding2026Beyond Chain-of-Thought: Rewrite as a Universal Interface for Generative Multimodal Embeddings2026FreeRet: MLLMs as Training-Free Retrievers2025UME-R1: Exploring Reasoning-Driven Generative Multimodal Embeddings2025