MMEB-v-2

The 'MMEB-V-2' dataset/benchmark contains a collection of multimodal data used to evaluate the performance of retrieval systems, particularly in the context of multimodal large language models (MLLMs).

Papers using MMEB-v-2 (10)

Qwen3-VL-Embedding and Qwen3-VL-Reranker: A Unified Framework for State-of-the-Art Multimodal Retrieval and Ranking2026 · 2 citese5-omni: Explicit Cross-modal Alignment for Omni-modal Embeddings2026 · 1 citesWAVE: Learning Unified & Versatile Audio-Visual Embeddings with Multimodal LLM2025 · 1 citesLaME: Learning to Think in Latent Space for Multimodal Embedding via Information Bottleneck2026MMEmb-R1: Reasoning-Enhanced Multimodal Embedding with Pair-Aware Selection and Adaptive Control2026Beyond Chain-of-Thought: Rewrite as a Universal Interface for Generative Multimodal Embeddings2026Embed-RL: Reinforcement Learning for Reasoning-Driven Multimodal Embeddings2026Reason to Contrast: A Cascaded Multimodal Retrieval Framework2026FreeRet: MLLMs as Training-Free Retrievers2025VLM2Vec-V2: Advancing Multimodal Embedding for Videos, Images, and Visual Documents2025