Microsoft Research Asia (China)

MoTA: Cross-Modal Motion Transfer for Animating 3D Head Avatars via 2D Motion Tokens

We present MoTA , a cross-modal motion transfer framework that animates 3D head avatars using motion tokens extracted from 2D image pairs. Our method decodes these tokens into 3D motion features, which serve as key and query signals in a transformer that modulates the target trip...

Replanning human–robot collaborative tasks with vision–language models via semantic and physical dual–correction

Human–robot collaborative assembly requires robots to interpret ambiguous corrective instructions while producing physically executable motions. Vision–language models (VLMs) provide semantic reasoning but may select logically inconsistent targets or misjudge execution outcomes....

OrchAlign: Orchestrated Multimodal Alignment for Gene Expression Prediction

Abstract Motivation Gene expression prediction benefits from integrating DNA sequences and epigenomic signals. Existing approaches typically combine these modalities using simple operations such as concatenation or summation, without explicitly modeling fine-grained token-level c...

Artificial intelligence empowers full-stack histopathological diagnosis and prognosis of renal cell tumor: a multi-center study with external validation

BACKGROUND: The rapid advancement of digital pathology has opened unprecedented opportunities for intelligent diagnosis in renal cell tumor. However, there remains a significant gap in the availability of reliable deep learning models capable of comprehensive kidney cancer detect...