5 papers · 1 filter
Asymmetric Decision-Making in Online Knowledge Distillation:Unifying Consensus and Divergence
Zhaowei Chen, Borui Zhao, Yuchen Ge +3
Online Knowledge Distillation (OKD) methods streamline the distillation training process into a single stage, eliminating the need for knowledge transfer from a pretrained teacher…
LEDiT: Your Length-Extrapolatable Diffusion Transformer without Positional Encoding
Shen Zhang, Siyuan Liang, Yaning Tan +9
Diffusion transformers (DiTs) struggle to generate images at resolutions higher than their training resolutions. The primary obstacle is that the explicit positional encodings(PE),…
Cascade Prompt Learning for Vision-Language Model Adaptation
Ge Wu, Xin Zhang, Zheng Li +4
Prompt learning has surfaced as an effective approach to enhance the performance of Vision-Language Models (VLMs) like CLIP when applied to downstream tasks. However, current learn…
Revisiting Prompt Pretraining of Vision-Language Models
Zhenyuan Chen, Lingfeng Yang, Shuo Chen +3
Prompt learning is an effective method to customize Vision-Language Models (VLMs) for various downstream tasks, involving tuning very few parameters of input prompt tokens. Recentl…
HiDiffusion: Unlocking Higher-Resolution Creativity and Efficiency in Pretrained Diffusion Models
Shen Zhang, Zhaowei Chen, Zhenyu Zhao +3
Diffusion models have become a mainstream approach for high-resolution image synthesis. However, directly generating higher-resolution images from pretrained diffusion models will…