Profiles2022-2025
Hexiang Hu
University of Maryland, College Park
5Papers
0Last author
8Unique co-authors
0First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers5
- OmnixR: Evaluating Omni-modality Language Models on Reasoning across ModalitiesAuthor 2 of 13ICLR 2025
- Subject-driven Text-to-Image Generation via Apprenticeship LearningAuthor 2 of 8NeurIPS 2023 · 265 citations
- Re-Imagen: Retrieval-Augmented Text-to-Image GeneratorAuthor 2 of 4ICLR 2023 · 44 citations
- PreSTU: Pre-Training for Scene-Text UnderstandingAuthor 4 of 7ICCV 2023 · 39 citations
- MuRAG: Multimodal Retrieval-Augmented Generator for Open Question Answering over Images and TextAuthor 2 of 5EMNLP 2022 · 89 citations
