Jibing Gong

Recent advances in vision–language models (VLMs) have expanded their multimodal code generation capabilities, yet their ability to generate executable visualization code from plots, especially for complex 3D, animated, plot-to-plot transformations, or multi-library scenarios, remains underexplore...

Negative sampling plays a pivotal role in training recommendation systems with implicit feedback, where the effectiveness of negatives directly impacts model convergence and recommendation quality. The key challenge is to efficiently mine high-quality hard negatives from the massive item space. E...