← Search

Xuanyu Liu

2 accepted papers

2026

Newton-coupled Dual-Teacher Semi-supervised Learning Framework

ICML 2026poster

Most semi-supervised learning frameworks rely on a single teacher that transfers zero-order supervision through pseudo-labels, constraining the student to imitate categorical outputs without perceiving the loss geometry. This design often leads to unstable optimization and limited generalization und…

Cited by 0Source ↗Scholar ↗
2023

Taming Diffusion Models for Audio-Driven Co-Speech Gesture Generation

CVPR 2023poster

Animating virtual avatars to make co-speech gestures facilitates various applications in human-machine interaction. The existing methods mainly rely on generative adversarial networks (GANs), which typically suffer from notorious mode collapse and unstable training, thus making it difficult to learn…