Xin Gao

Generating realistic human-object interaction videos from text, images, audio, *and* pose is now possible, opening the door to automated content creation workflows.

LLM datasets aren't independent islands: tracing their lineage reveals hidden redundancy, benchmark contamination, and opportunities for more diverse training data.

Achieve state-of-the-art naturalness in singing voice conversion by decoupling linguistic content and style with a boundary-aware information bottleneck and high-frequency band completion, even with limited data.

DINO-VO's learned patch selection and differentiable bundle adjustment leapfrogs traditional heuristic feature extraction, achieving SOTA monocular visual odometry with impressive generalization.

A diffusion model can generate high-quality synthetic chromosome images, boosting anomaly detection by nearly 14% F1 score and reducing reliance on scarce real-world abnormal samples.