6 papers
Generative Modeling via Drifting
Mingyang Deng, He Li, Tianhong Li +2
Generative modeling can be formulated as learning a mapping f such that its pushforward distribution matches the data distribution. The pushforward behavior can be carried out iter…
Reconstruction of three-dimensional shapes of normal and disease-related erythrocytes from partial observations using multi-fidelity neural networks
Haizhou Wen, He Li, Zhen Li
Reconstruction of 3D erythrocyte or red blood cell (RBC) morphology from partial observations, such as microscope images, is essential for understanding the physiology of RBC aging…
TRiMM: Transformer-Based Rich Motion Matching for Real-Time multi-modal Interaction in Digital Humans
Yueqian Guo, Tianzhao Li, Xin Lyu +7
Large Language Model (LLM)-driven digital humans have sparked a series of recent studies on co-speech gesture generation systems. However, existing approaches struggle with real-ti…
SparseDM: Toward Sparse Efficient Diffusion Models
Kafeng Wang, Jianfei Chen, He Li +2
Diffusion models represent a powerful family of generative models widely used for image and video generation. However, the time-consuming deployment, long inference time, and requi…
Solving Inverse Problems via Diffusion Optimal Control
Henry Li, Marcus Pereira
Existing approaches to diffusion-based inverse problem solvers frame the signal recovery task as a probabilistic sampling episode, where the solution is drawn from the desired post…
Non-Normal Diffusion Models
Henry Li
Diffusion models generate samples by incrementally reversing a process that turns data into noise. We show that when the step size goes to zero, the reversed process is invariant t…