Wenbo Nie

Multi-iteration experience learning in LLMs can lead to capability collapse, but strategic adjustments in experience granularity and injection patterns can stabilize and enhance performance.

Unlock high-quality 3D part segmentation with minimal labeled data by repurposing existing 3D generative models.

Achieve state-of-the-art style transfer without any training by exploiting under-explored correspondence cues within pre-trained diffusion models.