Recent research has shown that fine-tuning diffusion models (DMs) with arbitrary rewards,
including non-differentiable ones, is feasible with reinforcement learning (RL) techniques, …

… Gengdai Liu is an assistant professor at Xian Daizi University’s School of Computers. Liu
has a PhD from Zhejiang University’s State Key Lab. Contact him at liugengdai@cad.zju.edu.cn …

We propose D-FLIP, a novel algorithm that dynamically displays a set of digital photos using
different principles for organizing them. A variety of requirements for photo arrangements …

In this paper, we present a novel method for editing stylistic human motions. We represent
styles as differences between stylistic and introduced neutral motions, including timing …

To generate human motions with various specific attributes is a difficult task because of high
dimensionality and complexity of human motions. This paper presents a novel human …

In this paper, we present a novel method to display a famous ancient Chinese painting for
the purpose of cultural heritage preservation. The framework of multi-projector display wall …

In recent years, machine learning techniques have been widely used in the synthesis of human
motions and many excellent results are achieved, by taking advantage of the mature and …

A virtual human is an effective interface for interacting with users and plays an important role
in carrying out certain tasks. As social networking sites are getting more and more popular, …

We present a novel L4RW (Laziness‐based Realistic Real‐time Responsive Rebalance in
Walking) technique to synthesize 4RW animations under unexpected external perturbations …

We propose D-FLIP, a novel algorithm that dynamically displays a set of digital photos using
different principles for organizing them. A combination of requirements for photo …