Jie Li

4 papers Baidu

• GSAlign: Geometric and Semantic Alignment Network for Aerial-Ground Person Re-Identification
• JailBound: Jailbreaking Internal Safety Boundaries of Vision-Language Models
• MDReID: Modality-Decoupled Learning for Any-to-Any Multi-Modal Object Re-Identification
• Sparse Meets Dense: Unified Generative Recommendations with Cascaded Sparse-Dense Representations