Jian Chen

Latest

• LoRA-Contextualizing: Adaptation of Large Multimodal Models for Multi-page Document Understanding (Proceedings of the International Conference on Learning Representations 2025)
• LLaVA-Read: Enhancing Reading Ability of Multimodal Language Models (arXiv 2024)
• MMR: Evaluating Reading Ability of Large Multimodal Models (arXiv 2024)
• TRINS: Towards Multimodal Language Models that Can Read (Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 2024)