Sitemap
A list of all the posts and pages found on the site. For you robots out there, there is an XML version available for digesting as well.
Pages
Yuchuan Deng — Ph.D. student at Renmin University of China working on multimodal large language models and video understanding.
Posts
portfolio
publications
Text-Based Face Retrieval: Methods and Challenges
Published in Chinese Conference on Biometric Recognition (CCBR), Oral, 2023
Text-based face retrieval with vision-language learning and a coarse-to-fine retrieval strategy.
Recommended citation: Yuchuan Deng, Qijun Zhao, Zhanpeng Hu, and Zixiang Xu. Text-Based Face Retrieval: Methods and Challenges. CCBR, 2023.
Download Paper
DAPL: Integration of Positive and Negative Descriptions in Text-Based Person Search
Published in IEEE International Conference on Multimedia & Expo (ICME), 2025
Integrating positive and negative descriptions for text-based person search.
Recommended citation: Yuchuan Deng, Zhanpeng Hu, Zijie Xin, Chuang Deng, and Qijun Zhao. DAPL: Integration of Positive and Negative Descriptions in Text-Based Person Search. ICME, 2025.
Download Paper
Empowering Small VLMs to Think with Dynamic Memorization and Exploration
Published in International Conference on Learning Representations (ICLR), 2026
Dynamic memorization and exploration for reliable reasoning in small vision-language models.
Recommended citation: Jiazhen Liu, Yuchuan Deng, and Long Chen. Empowering Small VLMs to Think with Dynamic Memorization and Exploration. ICLR, 2026.
Download Paper
Fundus-R1: Training a Fundus-Reading MLLM with Knowledge-Aware Reasoning on Public Data
Published in arXiv preprint, 2026
A fundus-reading multimodal large language model trained with knowledge-aware reasoning on public data.
Recommended citation: Yuchuan Deng, Qijie Wei, Kaiheng Qian, Jiazhen Liu, Zijie Xin, Bangxiang Lan, Jingyu Liu, Jianfeng Dong, and Xirong Li. Fundus-R1: Training a Fundus-Reading MLLM with Knowledge-Aware Reasoning on Public Data. arXiv preprint, 2026.
Download Paper
Benchmarking Foundation and Large Language Models for Few-Shot Medical Image Segmentation
Published in arXiv preprint, 2026
Benchmarking foundation and large language models for few-shot medical image segmentation.
Recommended citation: Jinghong Liu, Yuchuan Deng, Fanping Liu, Meng Huang, and Xirong Li. Benchmarking Foundation and Large Language Models for Few-Shot Medical Image Segmentation. arXiv preprint, 2026.
Download Paper