Xiaoye Qu

6

Papers

21

Total Citations

Papers (6)

Extrapolating and Decoupling Image-to-Video Generation Models: Motion Modeling is Easier Than You Think

Learning the Unlearned: Mitigating Feature Suppression in Contrastive Learning

From Head to Tail: Towards Balanced Representation in Large Vision-Language Models through Adaptive Data Calibration

Towards Stabilized and Efficient Diffusion Transformers through Long-Skip-Connections with Spectral Constraints

LLM-assisted Entropy-based Adaptive Distillation for Unsupervised Fine-grained Visual Representation Learning

Unsupervised Domain Adaptative Temporal Sentence Localization with Mutual Information Maximization