← Search

Xinye Yang

2 accepted papers

2026

Flow-Based Knowledge Transfer for Efficient Large Model Distillation

AAAI 2026technical

Traditional knowledge distillation relies on simple MSE or KL divergence losses that fail to capture the complex distributional relationships between teacher and student model representations. We propose FlowDistill, a novel distillation framework that employs normalizing flows to model and transfer

Cited by 0SourcePDFScholar
2025

FreqTS: Frequency-Aware Token Selection for Accelerating Diffusion Models

AAAI 2025technical

In this paper, we propose FreqTS, a novel Frequency-Aware Token Selection approach for accelerating diffusion models without requiring retraining. Diffusion models have gained significant attention in the field of image synthesis due to their impressive generative capabilities. However, these models…

Cited by 0SourcePDFScholar