ConceptFormer: Learning Adaptive Latent Concepts for Query-Document Alignment in Visual Document Retrieval
Visual document retrieval is a critical component of multimodal retrieval-augmented generation, aiming to identify query-relevant pages from document collections where evidence is distributed across text, layout, charts, and visual structures. Recent efforts toward finer-grained supervision primarily rely on textual descriptions or localized visual regions as evidence proxies. However, such supervision signals may either overlook complex visual structures or provide incomplete and inaccurate representations of the underlying evidence. To address these limitations, we propose ConceptFormer, a latent concept representation learning framework for visual document retrieval. ConceptFormer mode...
| Authors | Chunyi Peng, Zhipeng Xu, Yukun Yan et al. |
|---|---|
| Primary category | cs.CV |
| Published | 16 August 2026 |
| Last updated at source | 21 August 2026 |
Models and datasets referencing this paper
- hmhm1229/ConceptFormer-EvalDataset
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.