Jun Xie

TBSM achieves state-of-the-art FID scores by transforming generative modeling through a novel scattering mechanism that enhances sample-level efficiency and reduces noise.

AIR achieves unprecedented attack success rates against subject-agnostic face swapping models while maintaining high visual fidelity, without needing a surrogate model.

YouZhi-LLM achieves unprecedented concurrency and accuracy in financial LLMs by dramatically reducing KV-cache overhead, setting a new standard for deployment efficiency.

Achieve state-of-the-art low-light image enhancement with real-time inference using an extremely lightweight and unsupervised framework.

Train your UMM visual generation component on image-only data first and you'll get SOTA performance with a fraction of the compute.