Zijie Meng

MedUAG sets a new standard in medical multimodal models, achieving strong performance across diverse understanding and generation tasks with the largest dataset yet.

DentAgent outperforms senior specialists by 17.3 percentage points in multi-label diagnosis, revolutionizing multimodal dental reasoning with traceable evidence integration.

Motion transfer can now succeed across vastly different object categories, achieving state-of-the-art fidelity without relying on fixed structural correspondences.

TARS achieves robust camera and viewpoint control in video re-shooting without relying on 3D reconstruction or paired data, enabling the plausible synthesis of previously unseen regions.

Transferring camera motion across vastly different scales can now be done with over 3x improvement in accuracy without sacrificing visual quality.

DRIVE-CHOREO achieves unprecedented multi-view consistency and BEV mAP by choreographing latent tokens across diverse modalities in autonomous driving.

Fine-grained quality degradations can now be assessed without sacrificing semantic coherence, thanks to a novel two-stream architecture that redefines vision-language alignment.

OmniDirector achieves unprecedented control over camera motion in video generation, enabling director-level precision without relying on scarce cross-paired data.