| Date | Presenter | Topic | Slides |
| 20240925 | Jie Min | ViLAS2: Vision-Language Model Based Agent for Construction Site Safety Surveillance | Slides |
| 20241009 | ChengFeng Wu | SARES: a Site Activity Recognition and Evaluation System for construction safety | Slides |
| 20241023 | Feifan He | Human knowledge-enhanced LLM chatbot for prediction of intestinal disease progression in patients with Crohn disease | Slides |
| 20241106 | Zihui Zhao | Efficient Multi-Modal Large Language Models via Token Selection | Slides |
| 20241120 | Shuntian Wu | Unifying Medical Multi-Modal Generation via Cross-Guided Diffusion with Visual Invariant | Slides |
| 20241120 | Shuhan Huang | Compositional Exemplars for In-context Learning | Slides |
| 20241204 | Xinyu Yang | Inter-Departmental Ticket Processing Time Prediction using Multi-Task Learning | Slides |
| 20241218 | Naifan Zhang | Enhancing MovieChat with Keyframe Extraction for Efficient Long-Term Video Understanding | Slides |
| 20250102 | Penghao Yin | 3DFormer: Enhancing Snapshot Compressive Imaging Performance with 3D Gaussian Splatting | Slides |
| 20250115 | Yuanbo Tang | TBA | TBA |