Jing Dai

Clinical information can significantly enhance survival prediction accuracy when effectively integrated with multimodal data, as shown by CIGTSurv's state-of-the-art results.

Mamba, typically used for sequence modeling, now powers state-of-the-art cancer survival risk prediction by fusing histological data with AI-generated protein features, outperforming existing methods.

Forget training separate models for each video generation condition – Video2LoRA lets you control video semantics with a single, lightweight (150MB) model.

Monocular vision, combined with a physically-realistic simulator, enables a 70% speedup in robotic endoluminal surgery tasks.