UME-R1: Exploring Reasoning-Driven Generative Multimodal Embeddings

The remarkable success of multimodal large language models (MLLMs) has driven advances in multimodal embeddings, yet existing models remain inherently discriminative, limiting their ability to benefit from reasoning-driven generation paradigm. In this work, we pioneer the exploration of reasoning-driven generative embeddings, unifying embedding tasks within a generative paradigm. We propose UME-R1, a universal multimodal embedding framework consisting of a two-stage training strategy: a cold-start supervised fine-tuning equips the model with reasoning capabilities and enables it to generate both discriminative and reasoning-driven generative embeddings; a subsequent reinforcement learning enhances reasoning and further optimizes generative embedding quality. This pioneering work reveals four key insights: 1) reasoning-driven generative embeddings unlock substantial performance gains over conventional discriminative embeddings by leveraging the powerful generative reasoning capabilities of MLLMs; 2) discriminative and reasoning-driven generative embeddings are complementary, whose combined oracle performance far exceeding that of either alone; 3) RL can effectively enhance reasoning-driven generative embeddings, establishing a scalable optimization paradigm; 4) repeated sampling at inference boosts downstream task coverage (pass@k), highlighting the inference-time scalability potential of reasoning-driven generative embeddings. Evaluated on the MMEB-V2 benchmark across 78 tasks spanning video, image, and visual documents, UME-R1 significantly outperforms conventional discriminative embedding models and offers a foundation for more interpretable, reasoning-driven generative multimodal embeddings. Our datasets, models, and code are available at https://github.com/XMUDeepLIT/UME-R1.