想用一个模型同时搞定稀疏检索和稠密检索？UEmbed把两件事合成了一次前向，9B在MMEB-v2上分数还挺能打，多模态输入也支持。
UEmbed是首个解码器-only的多模态嵌入模型，能在一次前向传播中同时生成稀疏词级和稠密向量表示。该模型通过在输入后追加N个可学习特殊token，并将词表划分为N个不相交子集，实现两类嵌入的统一输出。UEmbed公开了2B、4B、9B三个规模版本，其中UEmbed-9B在MMEB-v2基准上达到稠密71.8、稀疏71.0的成绩，优于同训练数据规模的多模态嵌入模型RzenEmbed。在BEIR基准上，UEmbed与强稀疏和稠密基线保持竞争力，并验证了在效率与智能体应用上的实用性。
UEmbed: Unified Sparse and Dense Multimodal Embeddings
Sparse retrieval underpins modern search systems, from web search to retrieval-augmented generation. Existing work has introduced Learned Sparse Retrieval (LSR) to push beyond exact lexical matching toward richer semantics. Yet LSR has so far remained tied to encoder-style bidirectional architectures, and its extension to multimodal settings still relies heavily on auxiliary cross-modal modules. To address these limitations, we introduce UEmbed (Unified Embedding), a decoder-only multimodal embedding model that produces both sparse lexical and dense representations in one causal forward pass. UEmbed appends N learnable special tokens to the input and partitions the vocabulary into N disjoint subsets. Each token's causal hidden state predicts sparse weights over its assigned subset, and the N subsets are concatenated into the full sparse vector. Trained on public data, we release UEmbed at 2B, 4B, and 9B scales. UEmbed-9B reaches 71.8 (dense) and 71.0 (sparse) on MMEB-v2, outperforming multimodal embedding models trained on publicly available data (e.g., RzenEmbed). On BEIR, UEmbed also remains competitive with strong dense and sparse baselines. Furthermore, we demonstrate the practical utility of UEmbed across three dimensions: effectiveness, efficiency, and agentic applications. Overall, UEmbed offers a new paradigm: it unifies dense and sparse embeddings in one model, while further extending sparse retrieval to unify text and multimodal inputs.