PAPER ACCEPTED
Video2LoRA appears in CVPR 2026 Findings
Unified semantic-controlled video generation via per-reference-video LoRA.
Research milestones, academic moves, and selected updates from the lab timeline.
Unified semantic-controlled video generation via per-reference-video LoRA.
Advised by Prof. Jianbing Shen, with a focus on computer vision and generative video systems.
Working on controllable generation systems and efficient model adaptation.