Beyond Chain-of-Thought: Rewrite as a Universal Interface for Generative Multimodal Embeddings 事件

Beyond Chain-of-Thought: Rewrite as a Universal Interface for Generative Multimodal Embeddings arXiv:2604.22280v2 Announce Type: replace Abstract: Multimodal Large Language Models (MLLMs) have emerged as a promising foundation for universal multimodal embeddings. Recent studies have shown that reasoning-driven generative multimodal embeddings can outperform discriminative embeddings on several embedding tasks. However, Chain-of-Thought (CoT) reasoning tends to generate redundant thinking steps