UEmbed：統一的稀疏與稠密多模態嵌入

摘要

稀疏檢索支撐著現代搜尋系統，從網頁搜尋到檢索增強生成皆然。既有研究已引入學習式稀疏檢索（Learned Sparse Retrieval, LSR），以突破精確詞彙匹配、邁向更豐富的語意理解。然而，LSR迄今仍受限於編碼器式的雙向架構，且其延伸至多模態場景時，仍高度依賴輔助的跨模態模組。為了解決這些限制，我們提出UEmbed（Unified Embedding），這是一個僅含解碼器的多模態嵌入模型，能在單次因果前向傳播中同時產生稀疏詞彙與密集表示。UEmbed在輸入後附加N個可學習的特殊標記，並將詞彙表劃分為N個互不重疊的子集。每個標記的因果隱藏狀態對其分配的子集預測稀疏權重，再將N個子集串接成完整的稀疏向量。我們使用公開資料訓練，並釋出2B、4B與9B三種規模的UEmbed模型。UEmbed-9B在MMEB-v2上達到71.8（密集）與71.0（稀疏）的成績，優於使用公開資料訓練的多模態嵌入模型（如RzenEmbed）。在BEIR上，UEmbed亦能與強大的密集與稀疏基線模型保持競爭力。此外，我們從三個面向展示了UEmbed的實用價值：有效性、效率與代理型應用。整體而言，UEmbed開創了一種新的範式：它在單一模型中統一了密集與稀疏嵌入，並進一步將稀疏檢索延伸至文字與多模態輸入的統一處理。

English

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.