| Sep 28, 2026 | One first-author paper submitted to ICLR 2027. |
| Jul 31, 2026 | A co-authored paper has been accepted for an oral presentation (2.8%) at PRCV 2026. |
| Jul 25, 2026 | MiuGS has been accepted at ACM Multimedia 2026. The work studies a shared 3D representation for adversarial objects observed by cameras and LiDAR. The project repository is available. |
| Jun 04, 2026 | We co-organized the 6th AdvML Workshop on Safety of Vision-Language Agents at CVPR 2026, held on June 4 in Denver. The workshop brought together research on reliable visual and multimodal systems. |
| Apr 04, 2026 | Two co-authored papers on the 3D adversarial attacks submitted to ACM Multimedia 2026. |
| Feb 10, 2026 | One paper published by TPAMI 2026. This work (DynamicPAE) investigates and addresses the training challenges inherent in the end-to-end conditional generation of physical adversarial examples (PAEs). Code is now available at GitHub. |