6 papers
TeleBoost: A Systematic Alignment Framework for High-Fidelity, Controllable, and Robust Video Generation
Yuanzhi Liang, Xuan'er Wu, Yirui Liu +12
Post-training is the decisive step for converting a pretrained video generator into a production-oriented model that is instruction-following, controllable, and robust over long te…
Learning What to Trust: Bayesian Prior-Guided Optimization for Visual Generation
Ruiying Liu, Yuanzhi Liang, Haibin Huang +2
Group Relative Policy Optimization (GRPO) has emerged as an effective and lightweight framework for post-training visual generative models. However, its performance is fundamentall…
Contrast-Invariant Self-supervised Segmentation for Quantitative Placental MRI
Xinliu Zhong, Ruiying Liu, Emily S. Nichols +4
Accurate placental segmentation is essential for quantitative analysis of the placenta. However, this task is particularly challenging in T2*-weighted placental imaging due to: (1)…
On Diffusion Process in SE(3)-invariant Space
Zihan Zhou, Ruiying Liu, Jiachen Zheng +2
Sampling viable 3D structures (e.g., molecules and point clouds) with SE(3)-invariance using diffusion-based models proved promising in a variety of real-world applications, wherei…
Molecular Conformation Generation via Shifting Scores
Zihan Zhou, Ruiying Liu, Chaolong Ying +2
Molecular conformation generation, a critical aspect of computational chemistry, involves producing the three-dimensional conformer geometry for a given molecule. Generating molecu…
On Accelerating Diffusion-based Molecular Conformation Generation in SE(3)-invariant Space
Zihan Zhou, Ruiying Liu, Tianshu Yu
Diffusion-based generative models in SE(3)-invariant space have demonstrated promising performance in molecular conformation generation, but typically require solving stochastic di…