Yuwen Ji
My research focuses on multimodal learning, particularly on developing AI systems that integrate language, vision, human motion, embodied action, and structured reasoning.
Primary Research
-
Code
ICML 2026
Zero-Shot Text-to-Motion Evaluation using Video Language Models
-
Code
NIPS 2025
Learning to Rank for In-Context Example Retrieval
-
Code
AAAI 2025
Unaligned Message-Passing and Contextualized-Pretraining for Robust Geo-Entity Resolution
-
Code
AAAI 2024
Stratified GNN Explanations through Sufficient Expansion