Author

Peng-Jun Xie

h-index 11 View on Semantic Scholar

We have 2 of 28 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Aug 2026

UEmbed: Unified Sparse and Dense Multimodal Embeddings

UEmbed (Unified Embedding), a decoder-only multimodal embedding model that produces both sparse lexical and dense representations in one causal forward pass, offers a new paradigm: it unifies dense and sparse embeddings in one model, while further extending sparse retrieval to unify text and multimodal inputs.

Tingyu Song, Mingxin Li, Yanzhao Zhang et al. · 2 citations

#artificial intelligence Preprint Sep 2026

CORE: Improving Compositional Reasoning in MLLM Embedding via Reranker Distillation

CORE is proposed, which synthesizes candidate lists spanning five compositional matching levels and introduces a Rank-KL objective that trains the embedding model to reproduce the reranker's fine-grained ranking and compares contrastive learning, pairwise CoSENT, and listwise Rank-KL under the same data and tuning budg...

Tingyu Song, Mingxin Li, Yanzhao Zhang et al. · 0 citations