Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Tingyu Song

Tingyu Song

1 indexed paper

Recent (6 mo)
1
With code
0
Influential cites
0
Benchmarked
0

Publications per year

1
26

Top categories

Vision×1AI×1NLP×1Info Retrieval×1

Frequent co-authors

Mingxin Li1×
Yanzhao Zhang1×
Dingkun Long1×
Pengjun Xie1×
Zhijie Nie1×
Yilun Zhao1×

Research Timeline

2026
UEmbed: Unified Sparse and Dense Multimodal Embeddings

The paper introduces UEmbed, a decoder-only multimodal embedding model that produces both sparse lexical and dense representations in one forward pass.

Highlighted terms show continued research focus across papers

Papers

cs.CVcs.AIcs.CLEmpiricalRecentAug 3, 2026

UEmbed: Unified Sparse and Dense Multimodal Embeddings

Tingyu Song, Mingxin Li, Yanzhao Zhang, Dingkun Long +4 more

The paper introduces UEmbed, a decoder-only multimodal embedding model that produces both sparse lexical and dense representations in one forward pass.

View →