4 papers · 1 filter
EvoPrune: Early-Stage Visual Token Pruning for Efficient MLLMs
Yuhao Chen, Bin Shan, Xin Ye +1
Multimodal Large Language Models (MLLMs) have shown strong performance in vision-language tasks, but their inference efficiency is severely limited by the exponential growth of vis…
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),…
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…
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…