Mingshuang Luo | 罗明双

I am a last year Ph.D. student at the Institute of Computing Technology (ICT), Chinese Academy of Sciences (CAS), China, under the supervision of Prof. Hong Chang and Associate Prof. Ruibing Hou.

Before embarking on my doctoral studies, I worked as a Speech Recognition Algorithm Engineer at Xiaomi Group AI Lab from 2021.7 to 2022.8, supervised by Dr. Daniel Povey (IEEE Fellow). I obtained my master degree in computer technology from University of the Chinese Academy of Science in 2021.7, supervised by Prof. Shiguang Shan (IEEE Fellow) and Associate Prof. Shuang Yang.

Email  /  Google Scholar  /  Github

We present DreamActor-M2, a universal character image animation framework that reformulates motion conditioning as a spatiotemporal in-context learning task. Our design harnesses the inherent generative priors of video foundation models while facilitating a critical evolution toward pose-free, end-to-end motion transfer directly from raw videos.

We present FlowAct-R1, a novel framework that enables lifelike, responsive, and high-fidelity humanoid video generation for seamless real-time interaction.

We propose CLASP (CLIP-guided Adaptable Self-suPervised learning), a novel framework designed for unsupervised pretraining in human-centric visual tasks.

We propose Morph, a Motion-Free physics optimization framework, consisting of a Motion Generator and a Motion Physics Refinement module, for enhancing physical plausibility without relying on expensive real-world motion data.

We present M³GPT, an advanced Multimodal, Multitask framework for Motion comprehension and generation.