5 papers
CF-VLA: Efficient Coarse-to-Fine Action Generation for Vision-Language-Action Policies
Fan Du, Feng Yan, Jianxiong Wu +8
Flow-based vision-language-action (VLA) policies offer strong expressivity for action generation, but suffer from a fundamental inefficiency: multi-step inference is required to re…
Latent Bias Alignment for High-Fidelity Diffusion Inversion in Real-World Image Reconstruction and Manipulation
Weiming Chen, Qifan Liu, Siyi Liu +4
Recent research has shown that text-to-image diffusion models are capable of generating high-quality images guided by text prompts. But can they be used to generate or approximate…
Understanding the Implicit User Intention via Reasoning with Large Language Model for Image Editing
Yijia Wang, Yiqing Shen, Weiming Chen +1
Existing image editing methods can handle simple editing instructions very well. To deal with complex editing instructions, they often need to jointly fine-tune the large language…
Generative Semantic Coding for Ultra-Low Bitrate Visual Communication and Analysis
Weiming Chen, Yijia Wang, Zhihan Zhu +1
We consider the problem of ultra-low bit rate visual communication for remote vision analysis, human interactions and control in challenging scenarios with very low communication b…
Runge-Kutta Approximation and Decoupled Attention for Rectified Flow Inversion and Semantic Editing
Weiming Chen, Zhihan Zhu, Yijia Wang +1
Rectified flow (RF) models have recently demonstrated superior generative performance compared to DDIM-based diffusion models. However, in real-world applications, they suffer from…