 SGDiff: Scene Graph Guided Diffusion Model for Image Collaborative SegCaptioningAAAI Conference on Artificial Intelligence (AAAI), 2025 |
 PairHuman: A High-Fidelity Photographic Dataset for Customized Dual-Person GenerationInformation Fusion (Inf. Fusion), 2025 |
 Enhancing Adversarial Transferability in Visual-Language Pre-training Models via Local Shuffle and Sample-based AttackNorth American Chapter of the Association for Computational Linguistics (NAACL), 2025 |
 Improving Visual Recommendation on E-commerce Platforms Using Vision-Language ModelsACM Conference on Recommender Systems (RecSys), 2025 |
