Yupeng Hu

FashionAM revolutionizes fashion image retrieval by directly linking multimodal queries to visual embeddings, eliminating the pitfalls of textification.

RankVR achieves a significant leap in Composed Image Retrieval by effectively managing noisy data, outperforming state-of-the-art methods in challenging scenarios.

Selective multimodal correction can dramatically enhance document parsing accuracy without compromising the integrity of reliable outputs.

ChartLens combines data correction and summary refinement to achieve state-of-the-art performance in chart understanding, outperforming existing solutions.