 mmE5: Improving Multimodal Multilingual Embeddings via High-quality Synthetic DataAnnual Meeting of the Association for Computational Linguistics (ACL), 2025 |
 VLM2Vec: Training Vision-Language Models for Massive Multimodal Embedding TasksInternational Conference on Learning Representations (ICLR), 2024 |
 MM-Embed: Universal Multimodal Retrieval with Multimodal LLMsInternational Conference on Learning Representations (ICLR), 2024 |
