On-policy distillation from multiple teachers combines expertise from different domains in a single student, but conflicting gradients can hinder this integration. Gradient corrections directly constrain parameter updates under plain SGD. With optimizers such as AdamW, however, momentum, adaptive scaling, and weight de...
Tao-Jie Zhu, Jing Jin, Yuan Xia et al.· 0 citations
Multi-modal object re-identification exploits complementary RGB, near-infrared (NIR), and thermal-infrared (TIR) observations to retrieve target objects. However, existing methods commonly employ visual encoders optimized for global image-text alignment and select tokens using learned importance scores. Such designs fa...
Wan-Ke Xia, Rui-Ding Zhu, Xing-Guo Xu et al.· 0 citations
EffectLearner is proposed, a semantic-reasoning-enhanced framework that combines a VLM-based Object-Effect Reasoner with a DiT-based Video Eraser that achieves clear advantages on both EffectWorld-Eval and the challenging EffectWorld-Wild, demonstrating its ability to deliver high-quality video object removal in comple...
Fei Wu, Wan-Ke Xia, Xu He et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
