7 papers
SemDynReg: Semantics-Guided Deformation Regularization for Dynamic 3D Gaussian Splatting
Ruitao Chen, Mozhang Guo, Jinge Li
Deformable 3D Gaussian Splatting (3DGS) has emerged as an efficient approach for rendering dynamic scenes in a wide range of 3D applications. However, existing deformation field-ba…
OmniVideo-R1: Reinforcing Audio-visual Reasoning with Query Intention and Modality Attention
Zhangquan Chen, Jiale Tao, Ruihuang Li +10
While humans perceive the world through diverse modalities that operate synergistically to support a holistic understanding of their surroundings, existing omnivideo models still f…
Luminark: Training-free, Probabilistically-Certified Watermarking for General Vision Generative Models
Jiayi Xu, Zhang Zhang, Yuanrui Zhang +4
In this paper, we introduce \emph{Luminark}, a training-free and probabilistically-certified watermarking method for general vision generative models. Our approach is built upon a…
Towards Infant Sleep-Optimized Driving: Synergizing Wearable and Vehicle Sensing in Intelligent Cruise Control
Ruitao Chen, Mozhang Guo, Jinge Li
Automated driving (AD) has substantially improved vehicle safety and driving comfort, but their impact on passenger well-being, particularly infant sleep, is not sufficiently studi…
Feedback-Driven Vision-Language Alignment with Minimal Human Supervision
Giorgio Giannone, Ruoteng Li, Qianli Feng +3
Vision-language models (VLMs) have demonstrated remarkable potential in integrating visual and linguistic information, but their performance is often constrained by the need for ex…
New Sphere Packings from the Antipode Construction
Ruitao Chen, Jiachen Hu, Binghui Li +2
In this note, we construct non-lattice sphere packings in dimensions , , , , , , and , demonstrating record densities that surpass all previously docume…